Block chain-based anomaly detection method

Through the blockchain-based abnormal detection method, the identity of smart home devices is identified, the operation risks are evaluated and the operation risks are issued are issued, which solves the problem of misoperation of smart home devices and improves the security and stability of the device.

CN118942444AInactive Publication Date: 2024-11-12SHANGHAI JIZHIXUAN INFORMATION TECHNOLOGY CO LTD

Patent Information

Application Number
CN202410793737.7
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-06-19
Publication Date
2024-11-12
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

Smart home devices cannot recognize and stop abnormal operations when operating incorrectly, resulting in losses and dangers, and lack effective abnormal detection methods.

Method used

Anomaly detection method based on blockchain is used to identify and prevent abnormal operations by establishing an information collection database, identifying family members, judging whether voice commands are within the preset range, evaluating operation risks, issuing alarms and conducting self-tests.

Benefits of technology

Improve the security of equipment use, and prevent equipment from operating incorrectly by accurately identifying identities, judging abnormal operations, issuing warnings and self-detection, and ensure the normal operation of the equipment.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118942444A_ABST
    Figure CN118942444A_ABST
Patent Text Reader

Abstract

The invention discloses an anomaly detection method based on a block chain, and the method comprises the following steps: 1, building an information collection library, and presetting the voice instruction data of each family member; step 2, when the smart home device is awakened, identifying the identity of the family member; 3, when the main family member sends a voice instruction, judging whether the voice instruction is within a preset range of the member; 4, when the voice instruction is not within the preset range, judging the risk level of the operation based on the operation record of the family member; 5, risk assessment is carried out according to the risk level and the risk assessment threshold value, and an alarm is given for abnormal operation; 6, when the equipment is in the working state under the abnormal operation, the equipment conducts self-inspection, and when the working time under the abnormal operation reaches the upper limit of the preset time, the equipment is stopped and locked so as to guarantee normal working of the equipment, and the method has the advantages of being intelligent and accurate.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of blockchain, and in particular to an anomaly detection method based on blockchain. Background Art

[0002] Blockchain technology can be applied to the field of smart home. By using sensors in the Internet of Things, home device information can be stored on the blockchain, and information sharing and interconnection between home devices can be achieved under the premise of privacy protection. Although the smart home system is very convenient, smart devices can be controlled by voice. However, the elderly and children often cause smart devices to be misoperated due to triggering voice keywords. When the device continues to operate in this situation, it will cause certain losses and dangers. Smart devices cannot recognize this abnormal operation and stop it. Therefore, it is necessary to design an intelligent and accurate blockchain-based anomaly detection method. Summary of the invention

[0003] The purpose of the present invention is to provide a blockchain-based anomaly detection method to solve the problems raised in the above background technology.

[0004] In order to solve the above technical problems, the present invention provides the following technical solutions: a blockchain-based anomaly detection method, the method comprising the following steps: Step 1: Establish an information collection database and preset the voice command data of each family member; Step 2: When the smart home device is awakened, it identifies the family member; Step 3: When a primary family member issues a voice command, determining whether the voice command is within the preset range of the member; Step 4: When the voice command is not within the preset range, the risk level of the operation is determined based on the operation records of the family members; Step 5: Alert abnormal operations based on risk assessment; Step 6: When the device is in an abnormal operating state, the device performs a self-check.

[0005] According to the above technical solution, the step of establishing an information collection database and presetting the voice command data of each family member includes: The smart home system has preset voice command ranges for each family member, establishes a corresponding data account for each family member, and records the normal control command range of each smart home device of the family member.

[0006] According to the above technical solution, when the smart home device is awakened, the step of identifying the identity of the family member includes: When a family member wakes up the smart home device through a voice command, the smart home device collects the voice data of the family member, identifies the family member through the voice recognition module and logs into the family member's data account; When a family member speaks, the smart home device extracts acoustic features, and the voice command recognition module matches the voice model of each family member and selects the identity with the highest match to the model as the issuer of the voice command.

[0007] According to the above technical solution, when a primary family member issues a voice command, the step of determining whether the voice command is within the preset range of the member includes: The preset range of the smart device includes time, switch, gear, and function. When the main family member issues a voice command, it detects whether the current time is within the preset time range, whether the device is open to the current family member, whether the current gear is between the preset gears, and whether the current function meets the preset function; When the voice command is within the preset range, it is determined that the family member is operating the smart home device normally; when any of the voice commands exceeds the preset range, it is determined that the family member may have performed an abnormal operation, and the current voice command is subsequently detected.

[0008] According to the above technical solution, when the voice command is not within the preset range, the step of judging the risk level of the operation based on the operation records of the family members includes: S1. Read the family member operation log to obtain the family member's operation record; S2. Extract the records of smart device on / off, gear position, function, and usage time in the operation records; S3. The extracted records are used as features for judging abnormal operations, and feature values ​​are set as s1, s2, ... sn; S4. Assign a weight to each feature and automatically set the weights through machine learning. The weights are w1, w2, ...wn. Then multiply the value of each feature by the corresponding weight, and then add the products to get the risk level of this operation s = w1 * s1 + w2 * s2 + ... + wn * sn.

[0009] According to the above technical solution, the step of issuing an alarm for abnormal operation based on risk assessment includes: When the risk level exceeds the risk assessment threshold by less than 60%, an alarm will be issued for this behavior, and a voice prompt will be issued to confirm whether to perform this operation again; when it exceeds the threshold by 60%, an alarm will be issued for this behavior, and a voice prompt will be issued to confirm whether to perform this operation again, and this operation will be sent to the APP for an alarm, and the APP can terminate this operation; Based on the risk assessment of abnormal operations, the smart home device will not execute the operation immediately, but will warn that the operation may be abnormal and will only execute the operation of the voice command after confirming and receiving a response again; when the operation risk assessment level is high, the smart home device will also warn that the operation may be abnormal and will only execute the operation of the voice command after confirming and receiving a response again. In addition, the smart home device will also link with the APP, and family members on the APP side can stop the abnormal operation based on their own judgment.

[0010] According to the above technical solution, when the device is in an abnormal operating state, the step of the device performing a self-check includes: When the device determines that an operation is an abnormal operation, it marks the current state as an abnormal state; In an abnormal state, the device will start self-checking. According to the preset upper limit of the abnormal state working time of the device, when the device operation time reaches the upper limit, the device will be stopped and locked, and the abnormal log will be sent to the APP. The APP will receive the alarm and decide whether to unlock the device.

[0011] According to the above technical solution, the blockchain-based anomaly detection system includes: A voice command recognition module, used to recognize the voice commands of family members and convert them into text form; An information collection library module is used to store the voice command data of each family member; A member identification module is used to identify the identity of the current family members according to the voice command; A preset range determination module is used to determine whether the current voice command is within the preset range of the current family member; The risk assessment module is used to assess the operational risks based on the behavior records and usage frequency of family members; An alarm module is used to send an alarm to family members when abnormal operation is found; The self-check module is used to perform self-check when the device is in an abnormal operation state to ensure the normal operation of the device; The device control module is used to control the switching, adjustment and setting of smart home devices.

[0012] According to the above technical solution, the preset range judgment module includes: The model matching unit is responsible for matching the voice command of the family member with the preset model to determine whether it is within the preset range; The threshold setting unit is used to set corresponding thresholds according to the needs or usage habits of family members to determine whether the voice command is an abnormal operation.

[0013] According to the above technical solution, the risk assessment module includes: A log recording unit, used to record the operation behaviors and usage frequency of family members when using smart home devices; A data processing unit is used to process and analyze the recorded behavior data of family members to find out the pattern of abnormal operation; The risk assessment algorithm unit is used to assess the operational risk using relevant risk assessment algorithms based on the data obtained through processing and analysis.

[0014] Compared with the prior art, the beneficial effects achieved by the present invention are: (1) The member identification module is provided to identify the identity of the current family member through voice recognition and accurately identify the identity; (2) By providing a preset range judgment module to judge whether the current voice command is within the preset range of the current family members, the safety of device use is improved; (3) A risk assessment module is set up to assess the operational risks based on the behavior records and usage frequency of family members, and intelligently identify abnormal operations; (4) By setting up an alarm module to send an alarm to family members when abnormal operation is detected, the safety of equipment use is improved; (5) A self-check module is provided to perform self-check when the equipment is in an abnormal operating state to ensure the normal operation of the equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings: Figure 1 is a flow chart of the method steps of the present invention; Figure 2 It is a schematic diagram of the system module composition of the present invention. DETAILED DESCRIPTION

[0016] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0017] Embodiment 1: Figure 1This is a flowchart of a blockchain-based anomaly detection method provided in Example 1 of the present invention. This embodiment can be applied to smart home scenarios. The method can be executed by a blockchain-based anomaly detection system provided in this embodiment. Figure 1 As shown, the method specifically comprises the following steps: Step 1: Establish an information collection database and preset the voice command data of each family member; In the embodiment of the present invention, the smart home system is preset with the voice command range of each family member. A corresponding data account is established for each family member to record the normal control command range of each smart home device of the family member; For example, family members include grandfather, grandmother, father, mother, son, and daughter. The smart home system presets the voice control command range for each person. For example, the son can control the lights in the room, including the switch of the lights, all brightness levels, and all lighting modes; the air conditioner in the room can be controlled, including the switch of the air conditioner, all air conditioner functions, air conditioner cooling 20℃-30℃, and air conditioner heating 22℃-28℃.

[0018] Step 2: When the smart home device is awakened, it identifies the family member; In the embodiment of the present invention, when a family member wakes up the smart home device through a voice command, the smart home device collects the voice data of the family member, identifies the family member's identity through the voice recognition module, and logs in the family member's data account. Family members need to collect and register their voices first, that is, establish their voice models in the system. When a family member speaks, the smart home device extracts acoustic features, and the voice command recognition module matches the voice model of each family member, and selects the identity with the highest matching degree with the model as the identity of the sender of the voice command; For example, the grandfather of the family wakes up the light in the living room through voice commands, collects the grandfather's voice data and recognizes the family member as the grandfather through the voice recognition module, and the system automatically logs in to the grandfather's account.

[0019] Step 3: When a primary family member issues a voice command, determining whether the voice command is within the preset range of the member; In an embodiment of the present invention, the preset range of the smart device includes time, switch, gear, and function. When a main family member issues a voice command, it is detected whether the current time is within the preset time range; whether the device is open to the current family member; whether the current gear is between the preset gears; and whether the current function meets the preset function. When the voice command is within the entire preset range, it is determined that the family member is operating the smart home device normally; when any of the voice commands exceeds the preset range, it is determined that the family member may have performed an abnormal operation, and the current voice command is subsequently detected. Through the above steps, the similarities and differences between the voice commands of the main family members and the preset voice commands are preliminarily screened out, and by presetting the normal usage of each family member, it is determined whether the voice command is a normal command, which facilitates the subsequent detection of abnormalities; For example, the range of the grandfather's control over the light is preset as follows: the grandfather can control the light switch at any time, the brightness level from level 2 to level 4, and all light modes. When the grandfather uses voice commands to turn on the light in the living room and controls the light level to level 3 through voice commands, the grandfather's voice command is detected to be within the preset range, and the voice command is determined to be normal. If the grandfather adjusts the light to level 5, the grandfather's voice command is detected to be outside the preset range, and the voice command is determined to be abnormal.

[0020] Step 4: When the voice command is not within the preset range, the risk level of the operation is determined based on the operation records of the family members; In the embodiment of the present invention, when the voice command is not within the preset range, it is determined that the operation of the family member who issued the command is abnormal. Based on the operation records of the family members, the risk of this abnormal operation can be determined, and the steps are as follows: S1. Read the family member operation log to obtain the family member's operation record; S2. Extract the records of smart device on / off, gear position, function, and usage time in the operation records; S3. The extracted records are used as features for judging abnormal operations, and feature values ​​are set as s1, s2, ... sn; S4. Assign a weight to each feature, and automatically set the weights through machine learning. The weights are w1, w2, ... wn. Then multiply the value of each feature by the corresponding weight, and then add the products to get the risk level of this operation s = w1 * s1 + w2 * s2 + ... + wn * sn; This step can determine the risk level of family members in abnormal operation by analyzing the data of family members using smart home devices, so as to issue an alarm for abnormal operation and prevent family members from operating abnormally by asking to confirm the operation; For example, the risk assessment threshold of a voice command of a smart home device is 10. For the voice control operation of the device, the following three features are considered: On / Off: preset on; Start time: preset 7:00-17:00; Gear: preset gear 2-4; Set different weights for each feature according to the actual situation, multiply the feature value by the weight, and add the product to get the current discovery assessment of 14.1; Since the risk assessment value exceeds 10, it can be judged that there is an abnormal operation risk in this operation.

[0021] Step 5: Alert abnormal operations based on risk assessment; In the embodiment of the present invention, the risk level of abnormal operation behavior is evaluated. When the risk level exceeds the risk assessment threshold by less than 60%, an alarm is issued for this behavior, and a voice prompt is issued to confirm again whether to perform this operation; when it exceeds the threshold by 60%, an alarm is issued for this behavior and a voice prompt is issued to confirm again whether to perform this operation, and this operation is sent to the APP for an alarm, and the APP can terminate this operation; Based on the risk assessment of abnormal operation, the smart home device will not execute the operation immediately, but will warn that the operation may be abnormal and confirm it again before executing the voice command. When the operation risk assessment level is high, the smart home device will also warn that the operation may be abnormal and confirm it again before executing the voice command. In addition, the smart home device will also link with the APP, and the family members on the APP side can stop the abnormal operation by their own judgment; For example, the risk assessment threshold of a voice command of a smart home device is 10. When the risk level of the voice command is 15, an alarm is issued for the voice operation and a question is asked whether to continue the operation. When the risk level is 19, an alarm is issued for the voice operation and a question is asked whether to continue the operation. The operation is sent to the APP for an alarm, and the family members on the APP end decide whether to terminate the operation based on their own judgment.

[0022] Step 6: When the device is in an abnormal operating state, the device performs a self-check; In the embodiment of the present invention, when the device determines that the operation is an abnormal operation, it marks the current state as an abnormal state. In the abnormal state, the device will start self-checking. According to the upper limit of the abnormal state working time preset by the device, when the device operation time reaches the upper limit, the device will be stopped and locked, and the abnormal log will be sent to the APP. The APP receives the alarm and decides whether to unlock the device; For example, when the operation of the main family member is determined to be an abnormal operation, the smart home device will mark the current state as an abnormal state. In the abnormal state, the device starts self-checking and detects the upper limit of the working time of the current device in the abnormal state according to the current gear. When the device operation time reaches the upper limit, the device stops operating and locks the device. Subsequent voice commands need to unlock the device to take effect. And when the abnormal log of this abnormal operation is sent to the APP, the APP side will receive an alarm, and the family members on the APP side will decide whether to unlock the device based on their own judgment.

[0023] Embodiment 2: Embodiment 2 of the present invention provides an anomaly detection system based on blockchain. Figure 2 A schematic diagram of the module composition of a blockchain-based anomaly detection system provided in Embodiment 2 of the present invention is shown in FIG. Figure 2 As shown, the system includes: A voice command recognition module, used to recognize the voice commands of family members and convert them into text form; An information collection library module is used to store the voice command data of each family member; A member identification module is used to identify the identity of the current family members according to the voice command; A preset range determination module is used to determine whether the current voice command is within the preset range of the current family member; The risk assessment module is used to assess the operational risks based on the behavior records and usage frequency of family members; An alarm module is used to send an alarm to family members when abnormal operation is found; The self-check module is used to perform self-check when the device is in an abnormal operation state to ensure the normal operation of the device; The device control module is used to control the switching, adjustment and setting of smart home devices.

[0024] In some embodiments of the present invention, the voice command recognition module includes: A recording unit, used to collect audio signals of voice commands of family members through a microphone; The signal processing unit is used to denoise, reduce noise, and enhance the sound of the collected voice signals in order to improve the accuracy of the voice commands; A feature extraction unit is used to extract features from the preprocessed speech signal to extract acoustic features that are meaningful for speech recognition; The speech recognition unit is used to convert the preprocessed speech signal into text form.

[0025] In some embodiments of the present invention, the preset range determination module includes: A model matching unit is used to match the voice command of the family member with the preset model to determine whether it is within the preset range; The threshold setting unit is used to set corresponding thresholds according to the needs or usage habits of family members to determine whether the voice command is an abnormal operation.

[0026] In some embodiments of the present invention, the risk assessment module includes: A log recording unit, used to record the operation behaviors and usage frequency of family members when using smart home devices; A data processing unit is used to process and analyze the recorded behavior data of family members to find out the pattern of abnormal operation; The risk assessment algorithm unit is used to assess the operational risk using relevant risk assessment algorithms based on the data obtained through processing and analysis.

[0027] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article 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, article or device.

[0028] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A blockchain-based anomaly detection method, characterized in that: The method comprises the following steps: Step 1: Establish an information collection database and preset the voice command data of each family member; Step 2: When the smart home device is awakened, it identifies the family member; Step 3: When a primary family member issues a voice command, determining whether the voice command is within the preset range of the member; Step 4: When the voice command is not within the preset range, the risk level of the operation is determined based on the operation records of the family members; Step 5: Alert abnormal operations based on risk assessment; Step 6: When the device is in an abnormal operating state, the device performs a self-check.

2. The blockchain-based anomaly detection method according to claim 1, characterized in that: The step of establishing an information collection database and presetting the voice command data of each family member includes: The smart home system has preset voice command ranges for each family member, establishes a corresponding data account for each family member, and records the normal control command range of each smart home device of the family member.

3. The blockchain-based anomaly detection method according to claim 1, characterized in that: When the smart home device is awakened, the step of identifying the identity of the family member includes: When a family member wakes up the smart home device through a voice command, the smart home device collects the voice data of the family member, identifies the family member through the voice recognition module and logs into the family member's data account; When a family member speaks, the smart home device extracts acoustic features, and the voice command recognition module matches the voice model of each family member and selects the identity with the highest match to the model as the issuer of the voice command.

4. The blockchain-based anomaly detection method according to claim 1, characterized in that: When a primary family member issues a voice command, the step of determining whether the voice command is within a preset range of the member includes: The preset range of the smart device includes time, switch, gear, and function. When the main family member issues a voice command, it detects whether the current time is within the preset time range, whether the device is open to the current family member, whether the current gear is between the preset gears, and whether the current function meets the preset function; When the voice command is within the preset range, it is determined that the family member is operating the smart home device normally; when any of the voice commands exceeds the preset range, it is determined that the family member may have performed an abnormal operation, and the current voice command is subsequently detected.

5. The blockchain-based anomaly detection method according to claim 1, characterized in that: When the voice command is not within the preset range, the step of determining the risk level of the operation based on the operation records of the family members includes: S1. Read the family member operation log to obtain the family member's operation record; S2. Extract the records of smart device on / off, gear position, function, and usage time in the operation records; S3. The extracted records are used as features for judging abnormal operations, and feature values ​​are set as s1, s2, ... sn; S4. Assign a weight to each feature and automatically set the weights through machine learning. The weights are w1, w2, ...wn. Then multiply the value of each feature by the corresponding weight, and then add the products to get the risk level of this operation s = w1 *s1 + w2 * s2 + ... + wn * sn.

6. The blockchain-based anomaly detection method according to claim 1, characterized in that: The step of issuing an alarm for abnormal operation according to risk assessment includes: When the risk level exceeds the risk assessment threshold by less than 60%, an alarm will be issued for this behavior, and a voice prompt will be issued to confirm whether to perform this operation again; when it exceeds the threshold by 60%, an alarm will be issued for this behavior, and a voice prompt will be issued to confirm whether to perform this operation again, and this operation will be sent to the APP for an alarm, and the APP can terminate this operation; Based on the risk assessment of abnormal operations, the smart home device will not execute the operation immediately, but will warn that the operation may be abnormal and will only execute the operation of the voice command after confirming and receiving a response again; when the operation risk assessment level is high, the smart home device will also warn that the operation may be abnormal and will only execute the operation of the voice command after confirming and receiving a response again. In addition, the smart home device will also link with the APP, and family members on the APP side can stop the abnormal operation based on their own judgment.

7. The blockchain-based anomaly detection method according to claim 1, characterized in that: When the device is in an abnormal operating state, the step of the device performing a self-check includes: When the device determines that an operation is an abnormal operation, it marks the current state as an abnormal state; In an abnormal state, the device will start self-checking. According to the preset upper limit of the abnormal state working time of the device, when the device operation time reaches the upper limit, the device will be stopped and locked, and the abnormal log will be sent to the APP. The APP will receive the alarm and decide whether to unlock the device.

8. A blockchain-based anomaly detection system, characterized by: The system includes: A voice command recognition module, used to recognize the voice commands of family members and convert them into text form; An information collection library module is used to store the voice command data of each family member; A member identification module is used to identify the identity of the current family members according to the voice command; A preset range determination module is used to determine whether the current voice command is within the preset range of the current family member; The risk assessment module is used to assess the operational risks based on the behavior records and usage frequency of family members; An alarm module is used to send an alarm to family members when abnormal operation is found; The self-check module is used to perform self-check when the device is in an abnormal operation state to ensure the normal operation of the device; The device control module is used to control the switching, adjustment and setting of smart home devices.

9. The blockchain-based anomaly detection system according to claim 8, characterized in that: The preset range determination module includes: The model matching unit is responsible for matching the voice command of the family member with the preset model to determine whether it is within the preset range; The threshold setting unit is used to set corresponding thresholds according to the needs or usage habits of family members to determine whether the voice command is an abnormal operation.

10. The blockchain-based anomaly detection system according to claim 8, characterized in that: The risk assessment module includes: A log recording unit, used to record the operation behaviors and usage frequency of family members when using smart home devices; A data processing unit is used to process and analyze the recorded behavior data of family members to find out the pattern of abnormal operation; The risk assessment algorithm unit is used to assess the operational risk using relevant risk assessment algorithms based on the data obtained through processing and analysis.

Citation Information

Patent Citations

  • Sound box control method, device, readable storage medium and mobile terminal

    CN108877790A

  • Smart home control method and device, computer equipment, and storage medium

    CN111258224A

  • Hierarchical authority unlocking method and device and storage medium

    CN111553192A

  • Voice control system for smart home

    CN113050445A

  • Method for managing threshold value of voice wake-up word of ceiling lamp

    CN113077788A

Cited By

  • Voice control method and system for wireless handheld ultrasonic equipment

    CN121506133A