An intelligent furniture collaborative design method

Abstract

The present invention discloses an intelligent furniture collaborative design method, which relates to the technical field of furniture collaborative processing, and includes the following steps: S1, collecting collaborative operation data packets of furniture devices to be processed; S2, calculating a plurality of importance scores according to the collaborative operation data packets of the furniture devices to be processed, and generating a performance evaluation sequence based on the plurality of importance scores; S3, determining a collaborative encryption key according to the performance evaluation sequence of the furniture devices to be processed, performing encryption, and storing the encrypted collaborative operation data packets in the cloud. The intelligent furniture collaborative design method designed by the present invention can finely evaluate the collaborative operation situation of furniture devices by calculating a plurality of importance scores in the collaborative operation data packets; and the present invention stores the encrypted collaborative operation data packets in the cloud, realizing remote access and sharing of data, and facilitating cross-device collaborative work.

Description

Technical Field

[0001] The present invention relates to the technical field of furniture collaborative processing, and particularly to an intelligent furniture collaborative design method. Background Art

[0002] With the rapid development of smart home technology, intelligent furniture, as an important part of smart home, its collaborative working ability directly affects the user experience and the intelligent level of the home environment. However, when intelligent furniture devices operate collaboratively, a large amount of operation data will be generated. These data not only contain the status information and working parameters of the devices, but may also involve user privacy and usage habits. Therefore, how to efficiently and securely process these collaborative operation data has become an urgent problem to be solved in the field of intelligent furniture design. Summary of the Invention

[0003] In order to solve the above problems, the present invention proposes an intelligent furniture collaborative design method.

[0004] The technical solution of the present invention is as follows: An intelligent furniture collaborative design method includes the following steps:

[0005] S1. Collect the collaborative operation data packets of the furniture devices to be processed;

[0006] S2. Calculate several importance scores based on the collaborative operation data packets of the furniture devices to be processed, and generate a performance evaluation sequence based on the several importance scores;

[0007] S3. Determine a collaborative encryption key according to the performance evaluation sequence of the furniture devices to be processed, perform encryption, and store the encrypted collaborative operation data packets in the cloud.

[0008] Further, in S1, the collaborative operation data packets of the furniture devices to be processed include the user behavior and interaction data of the furniture devices to be processed.

[0009] User behavior data reflects long-term habits and the user's personalization. Interaction data records the user's real-time operations.

[0010] Further, S2 includes the following sub-steps:

[0011] S21. Convert the collaborative operation data packets into JSON format as standard collaborative operation data packets;

[0012] S22. Determine the importance scores of each key-value pair in the standard collaborative operation data packets;

[0013] S23. Generate a performance evaluation sequence of the standard collaborative operation data packets based on the importance scores of all key-value pairs, the ID number of the furniture devices to be processed, and the remaining ID numbers of the devices associated with the furniture devices to be processed.

[0014] The beneficial effects of the above further solution are as follows: In the present invention, converting the collaborative operation data packet into the JSON format as the standard collaborative operation data packet can achieve unified representation and exchange of data, reducing the complexity of data processing. Determining the importance scores of each key-value pair in the standard collaborative operation data packet makes the evaluation of data more refined. By assigning importance scores to each key-value pair, the actual value of each key-value pair in collaborative work can be more accurately reflected. Generating a performance evaluation sequence based on the importance scores of all key-value pairs, the ID number of the furniture equipment to be processed, and the remaining ID numbers of the associated equipment takes into account information from multiple dimensions, making the performance evaluation more comprehensive and accurate.

[0015] Further, S22 includes the following sub-steps:

[0016] S221: Extract the values of several key-value pairs included in the standard collaborative operation data, randomly select several values from all the values of the key-value pairs, and split them into several sample subsets;

[0017] S222: Construct decision trees for each sample subset to generate a random forest;

[0018] S223: Use the random forest to extract the importance scores of each key-value pair in the standard collaborative operation data packet.

[0019] The beneficial effects of the above further solution are as follows: In the present invention, randomly selecting several values from all the values of the key-value pairs and splitting them into several sample subsets can avoid overfitting of data and improve the generalization ability of the random forest model. The randomness makes each sample subset have a unique combination of features, thus increasing the robustness of the random forest model. Constructing decision trees for each sample subset to generate a random forest makes use of the advantages of ensemble learning. The random forest accurately obtains the importance scores of each key-value pair by combining the prediction results of multiple decision trees.

[0020] Further, in S222, the maximum depth of the decision tree

[0021] ;

[0022] In the formula, represents the number of randomly selected values, represents the average number of child nodes generated after all nodes in the decision tree are split, represents a constant, represents the logarithmic function, represents rounding up.

[0023] That is, the ratio of the total number of all child nodes to the split node.

[0024] Further, S23 includes the following sub-steps:

[0025] S231. Perform hash processing on the keys of each key-value pair in the standard collaborative operation data packet to obtain the hash key values of each key-value pair;

[0026] S232. Generate the performance evaluation values of each key-value pair according to the importance scores and hash key values of each key-value pair, and form a performance evaluation sequence.

[0027] The beneficial effect of the above further solution is: In the present invention, the key itself serves as an identifier. In a key-value pair, it is used to uniquely or non-uniquely identify the corresponding value. In JSON data, the key is a string used to access a specific value; in a hash table, the key generates an index through a hash function, that is, the hash key value of the present invention.

[0028] Further, the performance evaluation value of the key-value pair has the following calculation formula:

[0029] ;

[0030] In the formula, represents the importance score of the key-value pair, represents the hash key value of the key-value pair, represents the out-of-bag error of the random forest, represents the hash value of the ID number of the furniture equipment to be processed, represents the sum of the hash values of the remaining ID numbers of the equipment associated with the furniture equipment to be processed.

[0031] The out-of-bag error of the random forest is a numerical value used to measure the prediction performance of the model on the samples (out-of-bag samples) that are not involved in the training of a single tree during the training process.

[0032] Further, S3 includes the following sub-steps:

[0033] S31. Calculate the feature parameters for the performance evaluation sequence;

[0034] S32. Convert the timestamp of the collaborative operation data packet collected for the furniture equipment to be processed into a Unix timestamp, and perform hash processing on the Unix timestamp to obtain the time parameter;

[0035] S33. Generate a collaborative encryption key based on the feature parameter and the time parameter.

[0036] The beneficial effects of the above further solution are as follows: In the present invention, the timestamp of the collaborative operation data packet of the furniture equipment to be processed is converted into a Unix timestamp, achieving the unification of time formats. The Unix timestamp is a widely accepted standard time format, facilitating time comparison and calculation across systems and platforms, and the obtained time parameter increases the security of time data. A collaborative encryption key is generated based on the feature parameter and the time parameter, combining information from two dimensions: performance evaluation and time. This multi-dimensional combination makes the encryption key more complex and unpredictable, improving the security of encryption.

[0037] Collaborative encryption key The expression of , represents the feature parameter, represents the time parameter.

[0038] Furthermore, in S31, the calculation formula for the feature parameter is as follows:

[0039] ;

[0040] In the formula, represents the performance evaluation value of the th key-value pair in the standard collaborative operation data packet, represents the performance evaluation value of the th key-value pair in the standard collaborative operation data packet, represents the performance evaluation value of the th key-value pair in the standard collaborative operation data packet, represents the total number of key-value pairs in the standard collaborative operation data packet.

[0041] The beneficial effects of the present invention are as follows: The intelligent furniture collaborative design method designed in the present invention can finely evaluate the collaborative operation situation of furniture equipment by calculating several importance scores in the collaborative operation data packet, generating a performance evaluation sequence; determining the collaborative encryption key through the performance evaluation sequence and the timestamp of the collaborative operation data packet ensures a close association between the encryption key and the equipment performance evaluation, improves the security and pertinence of encryption, effectively protects the confidentiality and integrity of the furniture equipment collaborative operation data, and prevents unauthorized access and tampering; and the present invention stores the encrypted collaborative operation data packet in the cloud, realizing remote access and sharing of data and facilitating cross-device collaborative work. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 is a flowchart of the intelligent furniture collaborative design method. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0043] The embodiments of the present invention will be further described below with reference to the drawings.

[0044] As Figure 1 shown, the present invention provides an intelligent furniture collaborative design method, including the following steps:

[0045] S1. Collect the collaborative operation data packets of the furniture equipment to be processed;

[0046] S2. Calculate a number of importance scores based on the collaborative operation data packets of the furniture equipment to be processed, and generate a performance evaluation sequence based on the number of importance scores;

[0047] S3. Determine a collaborative encryption key according to the performance evaluation sequence of the furniture equipment to be processed, perform encryption, and store the encrypted collaborative operation data packets in the cloud.

[0048] In the embodiment of the present invention, in S1, the collaborative operation data packets of the furniture equipment to be processed include the user behavior and interaction data of the furniture equipment to be processed.

[0049] The user behavior data reflects long-term habits and reflects the user's personalization. The interaction data records the user's real-time operations.

[0050] In the embodiment of the present invention, S2 includes the following sub-steps:

[0051] S21. Convert the collaborative operation data packets into JSON format as the standard collaborative operation data packets;

[0052] S22. Determine the importance scores of each key-value pair in the standard collaborative operation data packets;

[0053] S23. Generate a performance evaluation sequence of the standard collaborative operation data packets based on the importance scores of all key-value pairs, the ID number of the furniture equipment to be processed, and the remaining ID numbers of the associated equipment of the furniture equipment to be processed.

[0054] In the present invention, converting the collaborative operation data packets into JSON format as the standard collaborative operation data packets can realize the unified representation and exchange of data, and reduce the complexity of data processing. Determining the importance scores of each key-value pair in the standard collaborative operation data packets makes the evaluation of data more refined. By assigning importance scores to each key-value pair, the actual value in collaborative work can be more accurately reflected. Generating a performance evaluation sequence based on the importance scores of all key-value pairs, the ID number of the furniture equipment to be processed, and the remaining ID numbers of the associated equipment takes into account information from multiple dimensions, making the performance evaluation more comprehensive and accurate.

[0055] In the embodiment of the present invention, S22 includes the following sub-steps:

[0056] S221. Extract the values of several key-value pairs included in the standard collaborative operation data, randomly select several values from all the values of the key-value pairs, and split them into several sample subsets;

[0057] S222. Construct decision trees for each sample subset to generate a random forest;

[0058] S223. Use the random forest to extract the importance scores of each key-value pair in the standard collaborative operation data packet.

[0059] In the present invention, several values are randomly selected from all the values of the key-value pairs and split into several sample subsets to avoid overfitting of the data and improve the generalization ability of the random forest model. The randomness makes each sample subset have a unique combination of features, thus increasing the robustness of the random forest model. Constructing decision trees for each sample subset to generate a random forest makes use of the advantages of ensemble learning. The random forest accurately obtains the importance scores of each key-value pair by combining the prediction results of multiple decision trees.

[0060] In the embodiment of the present invention, in S222, the maximum depth of the decision tree The calculation formula is:

[0061] ;

[0062] In the formula, represents the number of randomly selected values, represents the average value of the number of child nodes generated after all nodes in the decision tree are split, represents a constant, represents the logarithmic function, represents rounding up.

[0063] That is, the ratio of the total number of all child nodes to the split node.

[0064] In the embodiment of the present invention, S23 includes the following sub-steps:

[0065] S231. Perform hash processing on the keys of each key-value pair in the standard collaborative operation data packet to obtain the hash key values of each key-value pair;

[0066] S232. Generate the performance evaluation values of each key-value pair according to the importance scores and hash key values of each key-value pair, and form a performance evaluation sequence.

[0067] In the present invention, the key itself serves as an identifier and is used to uniquely or non-uniquely identify the corresponding value in the key-value pair. In JSON data, the key is a string used to access a specific value; in a hash table, the key generates an index through a hash function, which is the hash key value of the present invention.

[0068] In the embodiment of the present invention, the performance evaluation value of the key-value pair has the following calculation formula:

[0069] ;

[0070] In the formula, represents the importance score of the key-value pair, represents the hash key value of the key-value pair, represents the out-of-bag error of the random forest, represents the hash value of the ID number of the furniture equipment to be processed, represents the sum of the hash values of the remaining ID numbers of the equipment associated with the furniture equipment to be processed.

[0071] The out-of-bag error of the random forest is a numerical value used to measure the prediction performance of the model on the samples (out-of-bag samples) that are not involved in the training of a single tree during the training process.

[0072] In the embodiment of the present invention, S3 includes the following sub-steps:

[0073] S31. Calculate the feature parameters for the performance evaluation sequence;

[0074] S32. Convert the timestamp of the collaborative operation data packet collected from the furniture equipment to be processed into a Unix timestamp, and perform a hash process on the Unix timestamp to obtain a time parameter;

[0075] S33. Generate a collaborative encryption key based on the feature parameter and the time parameter.

[0076] In the present invention, converting the timestamp of the collaborative operation data packet collected from the furniture equipment to be processed into a Unix timestamp realizes the unification of the time format. The Unix timestamp is a widely accepted standard time format, which is convenient for time comparison and calculation across systems and platforms. The obtained time parameter increases the security of the time data. Generating a collaborative encryption key based on the feature parameter and the time parameter combines the information in two dimensions of performance evaluation and time. This multi-dimensional combination makes the encryption key more complex and difficult to predict, improving the security of encryption.

[0077] The collaborative encryption key has the expression , represents the feature parameter, represents the time parameter.

[0078] In the embodiment of the present invention, in S31, the feature parameter has the following calculation formula:

[0079] ;

[0080] In the formula, Represents the performance evaluation value of the nth key-value pair in the standard collaborative operation data packet, Represents the performance evaluation value of the nth key-value pair in the standard collaborative operation data packet, Represents the performance evaluation value of the nth key-value pair in the standard collaborative operation data packet, Represents the total number of key-value pairs in the standard collaborative operation data packet.

[0081] Those of ordinary skill in the art will realize that the embodiments described herein are to assist the reader in understanding the principles of the present invention and should be understood that the scope of protection of the present invention is not limited to such specific statements and embodiments. Those of ordinary skill in the art can make various other specific deformations and combinations without departing from the essence of the present invention based on the technical revelations disclosed in the present invention, and these deformations and combinations are still within the scope of protection of the present invention.

Claims

1. An intelligent furniture collaborative design method, characterized in that, It includes the following steps: S1. Collect the collaborative operation data packets of the furniture equipment to be processed; S2. Calculate several importance scores based on the collaborative operation data packets of the furniture equipment to be processed, and generate a performance evaluation sequence based on the several importance scores; S3. Determine a collaborative encryption key according to the performance evaluation sequence of the furniture equipment to be processed, perform encryption, and store the encrypted collaborative operation data packets in the cloud; The S2 includes the following sub-steps: S21. Convert the collaborative operation data packets into JSON format as standard collaborative operation data packets; S22. Determine the importance scores of each key-value pair in the standard collaborative operation data packets; S23. Generate a performance evaluation sequence of the standard collaborative operation data packets based on the importance scores of all key-value pairs, the ID number of the furniture equipment to be processed, and the remaining ID numbers of the devices associated with the furniture equipment to be processed; The S22 includes the following sub-steps: S221. Extract the values of several key-value pairs included in the standard collaborative operation data, randomly select several values from the values of all key-value pairs, and split them into several sample subsets; S222. Build a decision tree for each sample subset to generate a random forest; S223. Use the random forest to extract the importance scores of each key-value pair in the standard collaborative operation data packets; In S222, the maximum depth of the decision tree is calculated by the following formula: ； In the formula, represents the number of randomly selected values, represents the mean of the number of child nodes generated after all nodes in the decision tree are split, represents a constant, represents a logarithmic function, represents rounding up.

2. The intelligent furniture collaborative design method according to claim 1, wherein, In the S1, the collaborative operation data packets of the furniture equipment to be processed include the user behaviors and interaction data of the furniture equipment to be processed.

3. The intelligent furniture collaborative design method according to claim 1, wherein The S23 includes the following sub-steps: S231. Perform hash processing on the keys of each key-value pair in the standard collaborative operation data packets to obtain the hash key values of each key-value pair; S232. Generate the performance evaluation values of each key-value pair according to the importance scores and hash key values of each key-value pair, and form a performance evaluation sequence.

4. The intelligent furniture collaborative design method according to claim 3, characterized in that, The performance evaluation value of the key-value pair The calculation formula is as follows: ； Wherein, represents the importance score of the key-value pair, represents the hash key value of the key-value pair, represents the out-of-bag error of the random forest, represents the hash value of the ID number of the furniture equipment to be processed, represents the sum of the hash values of the remaining ID numbers of the equipment associated with the furniture equipment to be processed.

5. The intelligent furniture collaborative design method according to claim 1, characterized in that The S3 includes the following sub-steps: S31. Calculate the characteristic parameters for the performance evaluation sequence; S32. Convert the timestamp of collecting the collaborative operation data packets of the furniture equipment to be processed into a Unix timestamp, and perform hash processing on the Unix timestamp to obtain a time parameter; S33. Generate a collaborative encryption key based on the characteristic parameters and the time parameter.

6. The intelligent furniture collaborative design method according to claim 5, characterized in that In the S31, the calculation formula of the characteristic parameter is as follows: ； In the formula, represents the performance evaluation value of the th key-value pair in the standard collaborative operation data packet, represents the performance evaluation value of the th key-value pair in the standard collaborative operation data packet, represents the performance evaluation value of the th key-value pair in the standard collaborative operation data packet, represents the total number of key-value pairs in the standard collaborative operation data packet.

Images