Sensing equipment communication method, system and equipment for intelligent transportation system

Abstract

The invention provides a sensing equipment communication method, system and equipment for an intelligent traffic system, and belongs to the technical field of traffic intelligent control. The method comprises the following steps: acquiring an initial communication message of sensing equipment based on a preset dual-mode detection mechanism; according to the initial communication message, determining a corresponding message protocol feature vector, and dynamically weighting each feature dimension through an information entropy weighting algorithm; and matching the weighted message protocol feature vector with a preset protocol fingerprint database to determine whether the initial communication message has a matching protocol. According to a protocol conversion rule corresponding to the matching result, the initial communication message is converted into first protocol data, and the initial communication message is compressed into second protocol data, so that the first protocol data and the second protocol data are synchronously sent to the management terminal; wherein the protocol conversion rule comprises: converting the initial communication message without the matching protocol based on the temporary protocol mapping rule, and converting the initial communication message based on the matching protocol.

Description

Technical Field

[0001] The present application relates to the technical field of intelligent traffic control, and in particular to a method, system and device for communication of sensing devices used in intelligent traffic systems. Background Art

[0002] With the rapid development of intelligent transportation systems, perception devices (such as cameras, radars, sensors, etc.) play an increasingly important role in traffic management, vehicle navigation, road condition monitoring, etc. However, intelligent transportation systems usually deploy a variety of heterogeneous perception devices, which may use different communication protocols and data formats, resulting in huge challenges in system integration and data interaction.

[0003] In the existing technology, the communication protocols of non-uniform sensing devices are usually identified and converted through manual configuration or pre-implanted protocol libraries. This method is difficult to fully cope with the protocol diversity problem of actually installed devices. At the same time, manual intervention is required to update the protocol when new devices are introduced, and the data sharing efficiency is low. In the scenario of installing a large number of sensing devices, the system deployment and maintenance costs are increased.

[0004] Based on this, there is an urgent need for a perception device communication technology solution for intelligent transportation systems to achieve efficient, flexible and adaptive perception device communication. Summary of the invention

[0005] To solve the above problems, the embodiments of the present application provide a method, system and device for communication of sensing devices in an intelligent transportation system.

[0006] On the one hand, an embodiment of the present application provides a sensing device communication method for an intelligent transportation system, the method comprising: Based on a preset dual-mode detection mechanism, an initial communication message of the sensing device is obtained; wherein the preset dual-mode detection mechanism includes sending a verification instruction set to the sensing device that establishes a communication connection and monitoring a power-on data packet from the sensing device; According to the initial communication message, determine the corresponding message protocol feature vector, and dynamically weight each feature dimension through an information entropy weighting algorithm; Matching the weighted message protocol feature vector with a preset protocol fingerprint library to determine whether the initial communication message has a matching protocol; According to the protocol conversion rules corresponding to the matching results, the initial communication message is converted into the first protocol data, and the initial communication message is compressed into the second protocol data, so that the first protocol data and the second protocol data are synchronously sent to the management terminal; wherein the protocol conversion rules include: converting the initial communication message without a matching protocol based on a temporary protocol mapping rule, and converting the initial communication message based on a matching protocol.

[0007] In one implementation of the present application, the verification instruction set includes at least one or more of the following: a protocol handshake instruction in a preset format, a compatibility detection instruction based on a standard protocol, and a test instruction of a random data field.

[0008] In one implementation of the present application, according to the initial communication message, a corresponding message protocol feature vector is determined, and each feature dimension is dynamically weighted by an information entropy weighting algorithm, specifically including: Extracting the message structure feature information corresponding to the initial communication message and encoding it into the corresponding message protocol feature vector; wherein the message structure feature information at least includes: a header field, a tail field, a check code type and a data segment length; According to the information entropy weighting algorithm and the historical feature vector samples corresponding to the message structure feature information, the feature weights of each feature dimension of the message protocol feature vector are determined, so as to dynamically weight the message protocol feature vector according to each feature weight.

[0009] In one implementation of the present application, the weighted message protocol feature vector is matched with a preset protocol fingerprint library to determine whether the initial communication message has a matching protocol, specifically including: Calculating the similarity of each feature dimension between the message protocol feature vector and each protocol feature vector in the preset protocol fingerprint library; wherein the feature dimension similarity is obtained based on the cosine similarity calculation of the corresponding feature dimension between the message protocol feature vector and the protocol feature vector; According to the feature weights and the feature dimension similarities, weighted summation is performed on the feature dimension similarities to determine the protocol similarity corresponding to the same protocol feature vector; Comparing the similarity of each of the protocols with a first preset threshold; In the case where the protocol similarity is greater than the first preset threshold, determining that the initial communication message has a matching protocol, and adding the fingerprint library protocol corresponding to the protocol similarity to the matching result; Otherwise, it is determined that there is no matching protocol for the initial communication message, and no matching protocol is used as the matching result.

[0010] In one implementation of the present application, the method further includes: In the case where it is determined that the initial communication message does not have a matching protocol, the initial communication message is input into a preset LSTM model to determine each key data field of the initial communication message; Dynamically map each of the key data fields with the fields in the preset standard protocol template to generate a temporary protocol mapping rule including a field mapping table and a verification rule conversion logic according to the dynamic mapping result.

[0011] In one implementation of the present application, a temporary protocol mapping rule including a field mapping table and a verification rule conversion logic is generated according to the dynamic mapping result, and the method further includes: The temporary protocol mapping rule is converted into a machine instruction by a just-in-time compiler, so as to convert the initial communication message into the first protocol data by the machine instruction.

[0012] In one implementation of the present application, after converting the initial communication message into the first protocol data and compressing the initial communication message into the second protocol data, the method further includes: Performing a byte difference comparison between the first protocol data and the second protocol data to obtain a comparison difference value; Accumulating a plurality of the comparison difference values ​​within a first preset number of cycles, and comparing each of the comparison difference values ​​with a second preset threshold; When the comparison difference values ​​corresponding to the second preset number of consecutive cycles are all smaller than the second preset threshold, the sending of the first protocol data is stopped, and temporary protocol mapping rule update prompt information is generated and sent to the management terminal.

[0013] In one implementation of the present application, the method further includes: Generate a difference change curve according to each of the comparison difference values; wherein the horizontal axis of the difference change curve is time, and the vertical axis is the value of the comparison difference value; Slide the preset sliding time window along the difference change curve with a preset step length to determine whether there is a communication anomaly in the difference change curve; wherein the communication anomaly is that the slope of the curve in the preset sliding time window is greater than a preset warning value; If so, generate device communication abnormality alarm information and send it to the management terminal, so as to update the preset protocol fingerprint library based on the feedback information from the management terminal.

[0014] On the other hand, an embodiment of the present application further provides a sensing device communication system for an intelligent transportation system, the system comprising: An acquisition module, configured to acquire an initial communication message of a sensing device based on a preset dual-mode detection mechanism; wherein the preset dual-mode detection mechanism includes sending a verification instruction set to the sensing device that establishes a communication connection and monitoring a power-on data packet from the sensing device; Determine a weighting module, which is used to determine the corresponding message protocol feature vector according to the initial communication message, and dynamically weight each feature dimension through an information entropy weighting algorithm; A matching module, used to match the weighted message protocol feature vector with a preset protocol fingerprint library to determine whether the initial communication message has a matching protocol; A conversion module is used to convert the initial communication message into first protocol data according to a protocol conversion rule corresponding to a matching result, and compress the initial communication message into second protocol data, so as to synchronously send the first protocol data and the second protocol data to a management terminal; wherein the protocol conversion rule includes: converting the initial communication message without a matching protocol based on a temporary protocol mapping rule, and converting the initial communication message based on a matching protocol.

[0015] On the other hand, the embodiment of the present application further provides a sensing device communication device for an intelligent transportation system, the device comprising: At least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute a perception device communication method for an intelligent transportation system as described above.

[0016] Compared with the prior art, the present invention has the following significant effects: Through the above technical solution, this application realizes the automatic discovery and message acquisition of the communication connection of the sensing device based on the dual-mode detection mechanism, which can reduce manual intervention. At the same time, the message protocol feature vector is dynamically weighted through the information entropy weighting algorithm, and the distinction of different feature dimensions is quantified, which improves the accuracy of protocol matching. It also combines the protocol fingerprint library matching and protocol conversion rules to automatically complete the standardized processing of unmatched protocol messages, which can be compatible with the communication needs of heterogeneous devices and reduce the deployment cost in a multi-protocol environment. In addition, through protocol data compression and multi-protocol data synchronous transmission, the network bandwidth occupancy is reduced, and the management terminal's parallel processing capabilities for original data and standardized data are guaranteed, thereby improving the utilization rate of communication resources. Therefore, this application effectively solves the problem of low efficiency and poor flexibility of traditional deployment relying on manual configuration, and provides highly compatible and low-latency communication support for intelligent transportation systems. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings: Figure 1A schematic diagram of a flow chart of a communication method for a sensing device in an intelligent transportation system according to an embodiment of the present application; Figure 2 This is a schematic diagram of the structure of a sensing device communication system for an intelligent transportation system in an embodiment of the present application; Figure 3 This is a schematic diagram of the structure of a sensing device communication device used in an intelligent transportation system in an embodiment of the present application. DETAILED DESCRIPTION

[0018] In order to make the purpose, technical solution and advantages of the present application clearer, the technical solution of the present application will be clearly and completely described below in combination with the specific embodiments of the present application and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present application.

[0019] The embodiments of the present application provide a method, system and device for communication of sensing devices for intelligent transportation systems, which are used to solve the technical problems that the current communication configuration of sensing devices is too dependent on manual work, the communication deployment is not intelligent enough, and the efficiency and flexibility are low.

[0020] The following describes in detail various embodiments of the present application in conjunction with the accompanying drawings.

[0021] The present application embodiment provides a sensing device communication method for an intelligent transportation system, such as Figure 1 As shown, the method may include steps S101-S104: S101, the microcontroller obtains the initial communication message of the sensing device based on the preset dual-mode detection mechanism.

[0022] Among them, the preset dual-mode detection mechanism includes sending a verification instruction set to the sensing device that establishes a communication connection and monitoring the power-on data packet from the sensing device.

[0023] It should be noted that the microcontroller as the execution subject of the communication method of the sensing device for the intelligent transportation system is only an example, and the execution subject is not limited to the microcontroller, and this application does not make specific restrictions on this. The microcontroller can be a device connecting the sensing device and the edge computing device or server, for example, set in the digital electronic simultaneous transmission centralized controller.

[0024] The sensing devices mentioned in this application include but are not limited to cameras installed on the road, geomagnetic vehicle detectors, environmental detection sensors, radar speed measurement equipment, etc.

[0025] This application can use a preset period of time after the sensing device is powered on and connected, and obtain the initial communication message of the sensing device through a preset dual-mode detection mechanism. The preset dual-mode detection mechanism is generally understood to use two different methods to obtain the initial communication message. One is to use an active detection module to actively send a verification instruction set to the sensing device that establishes a communication connection after the sensing device is powered on, and the other is to use a passive monitoring module to monitor the power-on data packet from the sensing device. The first method is more suitable for sensing devices that do not actively send power-on data packets, so that this application can be applied to more types of sensing devices. That is, the above-mentioned dual-mode detection combines the active sending of detection signals and the passive monitoring of device data, which can improve the coverage and accuracy of protocol identification. Active detection can trigger the response of the device and quickly identify known protocols; passive monitoring is suitable for devices that do not respond to detection signals but actively send data. The combination of the two can more comprehensively cover the communication characteristics of different devices and reduce the possibility of missed detection.

[0026] In the first method, as long as a physical connection is established with the sensing device, the active detection module will immediately send a verification instruction set containing multiple protocol handshake signals to the device. This is because active detection can quickly trigger device responses. For most devices that can respond to instructions normally, this method can efficiently obtain information related to their communication protocols. Even during the device initialization process, actively sending instructions can also obtain key information from its feedback for subsequent protocol identification. For example, for common camera devices that support the Transmission Control Protocol / Internet Protocol (TCP / IP) protocol, after establishing a physical connection, sending a verification instruction set is likely to receive a handshake response based on the TCP / IP protocol.

[0027] In the second method, from the moment the sensing device is powered on, the passive monitoring module begins to capture the power-on broadcast data packets during the device initialization phase in real time. This is mainly to deal with devices that may not be able to respond to the actively sent verification instruction set, such as some old devices or devices set to broadcast communication only in specific scenarios. They do not respond to active instructions, but will reveal clues about their own communication protocols through broadcast data packets during initialization. Passive monitoring can ensure that the protocol identification opportunities of such devices are not missed. Some environmental monitoring sensors may only broadcast their own configuration information at startup, and passive monitoring comes into play at this time.

[0028] The above-mentioned verification instruction set includes at least one or more of the following: protocol handshake instructions in a preset format, compatibility detection instructions based on standard protocols, and test instructions for random data fields. Among them, the protocol handshake instructions in a preset format can be set according to the actual usage scenario, and this application does not make specific restrictions on this. It can confirm the protocol version, parameters and basic compatibility of both parties in the communication initialization stage to establish a reliable communication foundation. Compatibility detection instructions based on standard protocols verify the device's adaptability to standard protocols (such as NTCIP, GB / T 20999) to ensure interoperability of core functions. Test instructions for random data fields can verify the device's fault tolerance and protocol robustness by injecting unconventional data to expose potential vulnerabilities. The verification instruction set of this application can also be used to trigger device responses by pre-setting the handshake signal format and sequence of multiple common communication protocols.

[0029] S102, the microcontroller determines the corresponding message protocol feature vector according to the initial communication message, and dynamically assigns weights to each feature dimension through an information entropy weighting algorithm.

[0030] In the embodiment of the present application, the above-mentioned method determines the corresponding message protocol feature vector according to the initial communication message, and dynamically weights each feature dimension through the information entropy weighting algorithm, specifically including: Extract the message structure feature information corresponding to the initial communication message and encode it into the corresponding message protocol feature vector. The message structure feature information includes at least: header field, tail field, checksum type and data segment length. According to the information entropy weighting algorithm and the historical feature vector samples corresponding to the message structure feature information, determine the feature weights of each feature dimension of the message protocol feature vector, so as to dynamically weight the message protocol feature vector according to each feature weight.

[0031] That is to say, this application can extract multi-dimensional features such as header field, tail field, checksum type and data segment length from the initial communication insulation. In addition, it can also identify multi-dimensional features including message header identification bit, data segment checksum bit distribution pattern, and timing response interval, so as to construct the message protocol feature vector of the initial communication message using multi-dimensional features. Subsequently, the information entropy weighting algorithm is used to dynamically weight each feature dimension, thereby improving the recognition weight of key feature items. The information entropy weighting algorithm calculates the information entropy of each feature dimension. and through Calculate information gain ,in is the preset number of samples. The feature weight of each feature dimension is calculated by the following formula :

[0032] in, is the number of feature dimensions. Each item in the message protocol feature vector has a unique feature weight corresponding to it.

[0033] S103, the microcontroller matches the weighted message protocol feature vector with a preset protocol fingerprint library to determine whether the initial communication message has a matching protocol.

[0034] In the embodiment of the present application, the weighted message protocol feature vector is matched with the preset protocol fingerprint library to determine whether the initial communication message has a matching protocol, specifically including: Calculate the similarity of each feature dimension between the message protocol feature vector and each protocol feature vector in the preset protocol fingerprint library. Among them, the feature dimension similarity is obtained based on the cosine similarity calculation of the corresponding feature dimension between the message protocol feature vector and the protocol feature vector. According to the weights of each feature and the similarity of each feature dimension, the similarities of each feature dimension are weighted and summed to determine the protocol similarity corresponding to the same protocol feature vector. Compare each protocol similarity with the first preset threshold. When the protocol similarity is greater than the first preset threshold, it is determined that the initial communication message has a matching protocol, and the fingerprint library protocol corresponding to the protocol similarity is added to the matching result. Otherwise, it is determined that the initial communication message does not have a matching protocol, and no matching protocol is used as the matching result.

[0035] In other words, the present application uses the cosine similarity calculation formula to calculate the cosine similarity between the message protocol feature vector and the protocol feature vector pre-stored in the preset protocol fingerprint library, that is, to calculate the cosine similarity of the feature values ​​of each feature dimension of the vector, and perform weighted processing to obtain the protocol similarity. The protocol similarity of the protocol feature vectors , is the first feature vector of the message protocol The feature value of feature dimension, For the The protocol feature vector The feature value of the feature dimension.

[0036] The similarity of each protocol is compared with the first preset threshold value, and the first preset threshold value is a value preset by the user, and this application does not specifically limit this. This application regards the initial communication message corresponding to the protocol similarity greater than the first preset threshold value as a message with a matching protocol, and then adds the matching protocol in the preset protocol fingerprint library to the matching result, so as to perform the operation of converting the initial communication message based on the matching protocol.

[0037] The present application regards the initial communication message corresponding to the protocol similarity less than or equal to the first preset threshold as a message without a matching protocol. At this time, the no matching protocol is used as the matching result to perform the operation of converting the initial communication message without a matching protocol based on the temporary protocol mapping rule.

[0038] The above scheme can quickly classify the initial communication messages, and can effectively improve the communication efficiency when the microcontroller of the present application is connected to several sensing devices.

[0039] In one embodiment of the present application, when it is determined that there is no matching protocol for the initial communication message, the initial communication message is input into a preset long short-term memory network (LSTM) model to determine each key data field of the initial communication message. Each key data field is dynamically mapped with a field in a preset standard protocol template to generate a temporary protocol mapping rule including a field mapping table and a verification rule conversion logic according to the dynamic mapping result.

[0040] That is to say, the present application is pre-trained with an LSTM model, which can be trained through a number of historical communication messages. The historical communication messages are marked with key data fields, which can be actively marked by experts or users. The present application does not make specific restrictions on this. Through the pre-trained LSTM model, the key data fields in the initial communication message can be identified. For example, when the initial communication message is input, the LSTM model will analyze the time series data of the message bit by bit, and use its memory unit and gating mechanism to capture the relationship between the data at different positions in the message, thereby determining the key data fields in the message. Specifically, in a communication message containing information such as vehicle speed and position, the LSTM model can identify fields representing speed data, fields representing position data, and so on.

[0041] The present application is also pre-set with a preset standard protocol template, which contains multiple fields for mapping and includes a variety of common or general protocol structure definitions. For the determined key data fields, dynamic mapping is to try to match these fields with the various fields in the standard protocol template. For example, a key data field is identified from the initial communication message, and its data format looks like a timestamp (such as a string of continuous numbers, and conforms to the approximate range of time representation). In the preset standard protocol template, there may be multiple protocol templates containing timestamp fields. The dynamic mapping process will compare the key data field with these possible timestamp fields, comparing their data format, length, value range and other features. If the timestamp field in a standard protocol template matches the identified key data field best in these features, a mapping relationship between the two is established. This mapping is not fixed, but is dynamically determined according to the specific key data field situation of each initial communication message, so it is called dynamic mapping.

[0042] The above field mapping table is a record of the dynamic mapping results. It records the correspondence between the key data fields identified from the initial communication message and the fields in the preset standard protocol template. For example: suppose a field A is identified from the initial communication message, and after dynamic mapping, it is found that it is the best match for field X1 in the preset standard protocol template X, then the field mapping table will record: field A->field X1 in the preset standard protocol template X. The field mapping table may also contain some additional information, such as field data type mapping (for example, the data type of field A in the initial communication message is an unsigned integer, and the data type of field X1 in the preset standard protocol template X is also an unsigned integer), the correspondence between field lengths, etc. In this way, when performing subsequent protocol conversion, the data in the initial communication message can be accurately converted according to the requirements of the target standard protocol template based on the field mapping table.

[0043] After the key data fields of the initial communication message are determined and dynamically mapped with the preset standard protocol template, the original verification rules of the initial communication message need to be converted to the verification rules of the target standard protocol template. For example, if the initial communication message uses a simple parity check, and the target standard protocol template uses the CRC-16 check in the standard CRC code. The verification rule conversion logic must first analyze the data range used for parity check in the initial communication message (which key data fields are involved in the check), and then determine how to recombine and calculate the CRC value for these key data fields according to the CRC-16 check requirements of the target standard protocol template. This may involve operations such as adjusting the byte order in the initial communication message (if the target protocol requires a different byte order) or padding the data (if the CRC calculation of the target protocol requires a specific data length) to generate a verification value that meets the verification rules of the target standard protocol template.

[0044] Examples of temporary protocol mapping rules: Field mapping table section: Device ID field (identified from the initial communication message) -> device identification field in the preset standard protocol template Y. Speed ​​data field (identified from the initial communication message) -> speed information field in the preset standard protocol template Y.

[0045] Verification rule conversion logic part: The initial communication message uses a simple cumulative sum check, and the target standard protocol template Y uses a CRC-8 check. The conversion logic is to reorganize the key data fields (such as the device ID field, speed data field, etc.) involved in the cumulative sum check in the initial communication message according to the calculation requirements of CRC-8, calculate the CRC-8 check value, and replace the original cumulative sum check value.

[0046] The temporary protocol mapping rules can convert the communication messages of the sensing device into a format that conforms to the preset standard protocol template in the subsequent communication process, so that the system can perform unified processing and analysis, and also provide a basis for subsequent possible protocol identification and optimization.

[0047] Through the above technical solution, when the microcontroller is connected to a sensing device that does not have a matching protocol, it can obtain the temporary protocol mapping rules corresponding to its communication message, so that the sensing devices that can be connected in this application are more extensive and not restricted by fixed protocols.

[0048] In another embodiment of the present application, the method for generating a temporary protocol mapping rule including a field mapping table and a verification rule conversion logic according to the dynamic mapping result further includes: The temporary protocol mapping rule is converted into a machine instruction by a just-in-time compiler, so as to convert the initial communication message into the first protocol data by the machine instruction.

[0049] In other words, the present application can use a just-in-time compiler to convert temporary protocol mapping rules into machine instruction-level parsing logic, achieve real-time optimization of protocol conversion, reduce the time delay of protocol conversion, and ensure the communication efficiency of perception devices.

[0050] S104, the microcontroller converts the initial communication message into the first protocol data according to the protocol conversion rule corresponding to the matching result, and compresses the initial communication message into the second protocol data, so as to synchronously send the first protocol data and the second protocol data to the management terminal.

[0051] The protocol conversion rules include: converting an initial communication message without a matching protocol based on a temporary protocol mapping rule, and converting an initial communication message based on a matching protocol.

[0052] That is to say, after obtaining the matching result according to the matching operation of S103 above, the message conversion can be performed according to the protocol conversion rule corresponding to the matching result, specifically, the temporary protocol mapping rule is used for message conversion and the matching protocol is used for message conversion. Subsequently, the converted first protocol data is sent to the management terminal, and the original initial communication message is also compressed into the second protocol data, and sent to the management terminal synchronously. The management terminal can be understood as a mobile phone, computer or other device of a traffic control or management department personnel, and this application does not make specific restrictions on this. Transmitting the second protocol data to the management terminal can avoid errors in message conversion, and at the same time, message backup can be performed, which can deal with data loss caused by malicious attacks or human errors to a certain extent.

[0053] In the embodiment of the present application, after converting the initial communication message into the first protocol data and compressing the initial communication message into the second protocol data, the method further includes: Perform byte difference comparison between the first protocol data and the second protocol data to obtain a comparison difference value. Accumulate multiple comparison difference values ​​within a first preset number of cycles, and compare each comparison difference value with a second preset threshold. When each comparison difference value corresponding to a second preset number of consecutive cycles is less than the second preset threshold, stop sending the first protocol data, generate a temporary protocol mapping rule update prompt message, and send it to the management terminal.

[0054] In other words, the present application can perform a difference comparison according to bytes. The first protocol data is the data after the message conversion through the communication protocol that the subsequent signal receiving terminal can recognize. The second protocol data is the data after the initial communication message sent directly from the perception device is compressed. When the byte difference is the same, it is recorded as 0, and the difference is recorded as 1, and the comparison difference value is accumulated. In the process of continuous communication with the perception device, the present application can receive several communication messages from the perception device, and then several comparison difference values ​​corresponding to the moment will be obtained. The present application presets a communication cycle, and accumulates multiple comparison difference values ​​within a first preset number of cycles preset by the user. At this time, the accumulated comparison difference values ​​are compared with the second preset threshold value. The second preset threshold is set by the user according to the actual usage scenario, and is not specifically limited here. If the present application monitors that the comparison difference values ​​of the second preset number of consecutive cycles are all less than the second preset threshold, the first protocol data will be stopped at this time. The second preset number is less than the first preset number.

[0055] For example, the first preset number is 10, and the comparison difference values ​​within 10 cycles are {a1, a2, a3, ..., a10}. If the comparison difference values ​​{a4, a5, a6, a7, a8, a9} in 6 consecutive cycles of the second preset number are all less than the second preset threshold, then the sending of the above-mentioned first protocol data is stopped, and a temporary protocol mapping rule update prompt message is generated and sent to the management terminal so that manual intervention can be performed to update the temporary protocol mapping rule.

[0056] The above solution can avoid the problem that the temporary protocol mapping rule converts the communication message too much and the authenticity of the communication result cannot be guaranteed.

[0057] In one embodiment of the present application, the message conversion of the sensing device communication may also be caused by a conversion anomaly in the matching protocol. Therefore, the present application provides the following embodiments, including: A difference change curve is generated according to each comparison difference value. The horizontal axis of the difference change curve is time, and the vertical axis is the value of the comparison difference value. The preset sliding time window is slid along the difference change curve with a preset step size to determine whether there is a communication anomaly in the difference change curve. The communication anomaly is that the slope of the curve within the preset sliding time window is greater than the preset warning value. When it is determined that there is a communication anomaly in the difference change curve, a device communication anomaly alarm message is generated and sent to the management terminal to update the preset protocol fingerprint library based on the feedback information from the management terminal.

[0058] That is to say, the present application uses time as the horizontal coordinate and the comparison difference value as the vertical coordinate to establish a plane rectangular coordinate system, and generates a difference change curve through the comparison difference value obtained by the above steps. Through the preset sliding time window with a preset window size and a preset step length, the difference change curve is slid in sequence, and it is judged in real time whether the curve slope corresponding to the curve in the window is greater than the preset warning value. If so, the device communication abnormality alarm information is generated, and the device communication abnormality alarm information includes the time point at which the preset sliding time window is located at this time, and then the preset sliding time window continues to slide. If the curve slope is not greater than the preset warning value, the preset sliding time window continues to slide. The above-mentioned window size, preset step length and preset warning value can be set by the user according to the actual use scenario, or the default value can be selected, and this application does not make specific restrictions on this. After the management terminal receives the communication abnormality alarm information, it can send feedback information by itself. The feedback information can include the update time and update method of the preset protocol fingerprint library, for example, at XX day XX time, the preset protocol fingerprint library is manually updated.

[0059] Figure 2 A schematic diagram of a communication system for sensing devices used in an intelligent transportation system according to an embodiment of the present application is shown in FIG. Figure 2As shown, the sensing device communication system 200 for an intelligent transportation system includes: The acquisition module 201 is used to acquire the initial communication message of the sensing device based on the preset dual-mode detection mechanism. The preset dual-mode detection mechanism includes sending a verification instruction set to the sensing device that establishes a communication connection and monitoring the power-on data packet from the sensing device. The weighting module 202 is used to determine the corresponding message protocol feature vector based on the initial communication message, and dynamically weight each feature dimension through the information entropy weighting algorithm. The matching module 203 is used to match the weighted message protocol feature vector with the preset protocol fingerprint library to determine whether the initial communication message has a matching protocol. The conversion module 204 is used to convert the initial communication message into the first protocol data according to the protocol conversion rule corresponding to the matching result, and compress the initial communication message into the second protocol data, so as to send the first protocol data and the second protocol data to the management terminal synchronously. The protocol conversion rules include: converting the initial communication message without a matching protocol based on the temporary protocol mapping rule, and converting the initial communication message based on the matching protocol.

[0060] Figure 3 A schematic diagram of a structure of a sensing device communication device for an intelligent transportation system provided in an embodiment of the present application, such as Figure 3 As shown, the device includes: At least one processor; and a memory in communication with the at least one processor. The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to: Based on the preset dual-mode detection mechanism, the initial communication message of the sensing device is obtained. Among them, the preset dual-mode detection mechanism includes sending a verification instruction set to the sensing device that establishes a communication connection and monitoring the power-on data packet from the sensing device. According to the initial communication message, the corresponding message protocol feature vector is determined, and each feature dimension is dynamically weighted by an information entropy weighting algorithm. The weighted message protocol feature vector is matched with the preset protocol fingerprint library to determine whether the initial communication message has a matching protocol. According to the protocol conversion rule corresponding to the matching result, the initial communication message is converted into the first protocol data, and the initial communication message is compressed into the second protocol data, so that the first protocol data and the second protocol data are synchronously sent to the management terminal. Among them, the protocol conversion rules include: converting the initial communication message without a matching protocol based on the temporary protocol mapping rule, and converting the initial communication message based on the matching protocol.

[0061] Each embodiment in this application is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system and device embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiments.

[0062] The system and equipment provided in the embodiments of the present application correspond one-to-one to the method. Therefore, the system and equipment also have similar beneficial technical effects as the corresponding methods. Since the beneficial technical effects of the methods have been described in detail above, the beneficial technical effects of the system and equipment will not be repeated here.

[0063] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0064] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. A sensing device communication method for an intelligent transportation system, characterized in that: The method comprises: Based on a preset dual-mode detection mechanism, an initial communication message of the sensing device is obtained; wherein the preset dual-mode detection mechanism includes sending a verification instruction set to the sensing device that establishes a communication connection and monitoring a power-on data packet from the sensing device; According to the initial communication message, determine the corresponding message protocol feature vector, and dynamically weight each feature dimension through an information entropy weighting algorithm; Matching the weighted message protocol feature vector with a preset protocol fingerprint library to determine whether the initial communication message has a matching protocol; According to the protocol conversion rules corresponding to the matching results, the initial communication message is converted into the first protocol data, and the initial communication message is compressed into the second protocol data, so that the first protocol data and the second protocol data are synchronously sent to the management terminal; wherein the protocol conversion rules include: converting the initial communication message without a matching protocol based on a temporary protocol mapping rule, and converting the initial communication message based on a matching protocol.

2. A method for communication of sensing devices for intelligent transportation systems according to claim 1, characterized in that: The verification instruction set includes at least one or more of the following: a protocol handshake instruction in a preset format, a compatibility detection instruction based on a standard protocol, and a test instruction of a random data field.

3. A method for communication of sensing devices for intelligent transportation systems according to claim 1, characterized in that: According to the initial communication message, the corresponding message protocol feature vector is determined, and each feature dimension is dynamically weighted by an information entropy weighting algorithm, specifically including: Extracting the message structure feature information corresponding to the initial communication message and encoding it into the corresponding message protocol feature vector; wherein the message structure feature information at least includes: a header field, a tail field, a check code type and a data segment length; According to the information entropy weighting algorithm and the historical feature vector samples corresponding to the message structure feature information, the feature weights of each feature dimension of the message protocol feature vector are determined, so as to dynamically weight the message protocol feature vector according to each feature weight.

4. A method for communication of sensing devices for intelligent transportation systems according to claim 3, characterized in that: The weighted message protocol feature vector is matched with a preset protocol fingerprint library to determine whether the initial communication message has a matching protocol, specifically including: Calculating the similarity of each feature dimension between the message protocol feature vector and each protocol feature vector in the preset protocol fingerprint library; wherein the feature dimension similarity is obtained based on the cosine similarity calculation of the corresponding feature dimension between the message protocol feature vector and the protocol feature vector; According to the feature weights and the feature dimension similarities, weighted summation is performed on the feature dimension similarities to determine the protocol similarity corresponding to the same protocol feature vector; Comparing the similarity of each of the protocols with a first preset threshold; In the case where the protocol similarity is greater than the first preset threshold, determining that the initial communication message has a matching protocol, and adding the fingerprint library protocol corresponding to the protocol similarity to the matching result; Otherwise, it is determined that there is no matching protocol for the initial communication message, and no matching protocol is used as the matching result.

5. The method for communication of sensing devices for intelligent transportation system according to claim 1, characterized in that: The method further comprises: In the case where it is determined that the initial communication message does not have a matching protocol, the initial communication message is input into a preset LSTM model to determine each key data field of the initial communication message; Dynamically map each of the key data fields with the fields in the preset standard protocol template to generate a temporary protocol mapping rule including a field mapping table and a verification rule conversion logic according to the dynamic mapping result.

6. A method for communication of sensing devices for intelligent transportation systems according to claim 5, characterized in that: Generating a temporary protocol mapping rule including a field mapping table and a verification rule conversion logic according to the dynamic mapping result, the method further comprising: The temporary protocol mapping rule is converted into a machine instruction by a just-in-time compiler, so as to convert the initial communication message into the first protocol data by the machine instruction.

7. A method for communication of sensing devices for intelligent transportation systems according to claim 1, characterized in that: After converting the initial communication message into the first protocol data and compressing the initial communication message into the second protocol data, the method further includes: Performing a byte difference comparison between the first protocol data and the second protocol data to obtain a comparison difference value; Accumulating a plurality of the comparison difference values ​​within a first preset number of cycles, and comparing each of the comparison difference values ​​with a second preset threshold; When the comparison difference values ​​corresponding to the second preset number of consecutive cycles are all smaller than the second preset threshold, the sending of the first protocol data is stopped, and temporary protocol mapping rule update prompt information is generated and sent to the management terminal.

8. A method for communication of sensing devices for intelligent transportation systems according to claim 7, characterized in that: The method further comprises: Generate a difference change curve according to each of the comparison difference values; wherein the horizontal axis of the difference change curve is time, and the vertical axis is the value of the comparison difference value; Slide the preset sliding time window along the difference change curve with a preset step length to determine whether there is a communication anomaly in the difference change curve; wherein the communication anomaly is that the slope of the curve in the preset sliding time window is greater than a preset warning value; If so, generate device communication abnormality alarm information and send it to the management terminal, so as to update the preset protocol fingerprint library based on the feedback information from the management terminal.

9. A sensing device communication system for an intelligent transportation system, characterized in that: The system comprises: An acquisition module, configured to acquire an initial communication message of a sensing device based on a preset dual-mode detection mechanism; wherein the preset dual-mode detection mechanism includes sending a verification instruction set to the sensing device that establishes a communication connection and monitoring a power-on data packet from the sensing device; Determine a weighting module, which is used to determine the corresponding message protocol feature vector according to the initial communication message, and dynamically weight each feature dimension through an information entropy weighting algorithm; A matching module, used to match the weighted message protocol feature vector with a preset protocol fingerprint library to determine whether the initial communication message has a matching protocol; A conversion module is used to convert the initial communication message into first protocol data according to a protocol conversion rule corresponding to a matching result, and compress the initial communication message into second protocol data, so as to synchronously send the first protocol data and the second protocol data to a management terminal; wherein the protocol conversion rule includes: converting the initial communication message without a matching protocol based on a temporary protocol mapping rule, and converting the initial communication message based on a matching protocol.

10. A sensing device communication device for an intelligent transportation system, characterized in that: The device comprises: at least one processor; and, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute a perception device communication method for an intelligent transportation system as described in any one of claims 1 to 8.

Images