A number status identification method based on information security

Abstract

The present invention relates to the field of communication technology, and discloses a number status identification method based on information security, comprising the following steps: obtaining comprehensive information of disaster area numbers, obtaining historical communication data information of numbers before the disaster; obtaining first serial data based on the sorting of comprehensive information of disaster area numbers, and obtaining second serial data stream based on the sorting of historical communication data information of numbers before the disaster; inputting the first serial data stream and the second serial data stream into a number status identification model, and outputting the identification result of the disaster area number status and whether the pre-disaster number will be damaged in the disaster situation. The present invention can identify the status of numbers in the disaster area, and according to the identified number status, human and material resources can be deployed in a targeted manner to restore the communication in the disaster area as soon as possible.

Description

Technical Field

[0001] The present invention relates to the field of communication technology, and more specifically, to a number status identification method based on information security. Background Art

[0002] In modern society, the stability and reliability of communication networks are crucial, especially when natural disasters occur, timely information transmission can significantly improve rescue efficiency and reduce losses. However, when disasters occur, due to damage to terrain, climate and communication equipment, communication services in some areas are often severely affected, and many users are unable to use their phones to contact relatives and friends or seek help. Therefore, it is particularly important to understand the status of numbers in disaster areas.

[0003] With the development of artificial intelligence and big data technology, intelligent identification methods based on mobile communication data have been widely used. These methods can actively identify the number status in the disaster area by analyzing and processing a large amount of communication data, providing a scientific basis for emergency management. Summary of the invention

[0004] The present invention provides a number status identification method based on information security, which aims to improve the communication guarantee and information transmission efficiency when a disaster occurs. The method includes the following steps: first, the comprehensive information of the number in the disaster area is obtained, and the historical communication data information of the number before the disaster is obtained. This information covers the signal strength, communication records and historical operation data of the base station before the disaster. The two information streams are input into a constructed number status identification model, which includes multiple encoders and fusion layers. By extracting and fusing features, the communication status of the number under the disaster condition is comprehensively judged, and an assessment of whether the number may be damaged is given, which solves the technical problem of the difficulty of number status identification in the disaster environment.

[0005] The present invention provides a number status identification method based on information security, comprising the following steps:

[0006] Step 100, obtaining comprehensive information of disaster area numbers, including: disaster area number information, base station information, and disaster area user information; obtaining historical communication data information of pre-disaster numbers, including: historical signal strength of pre-disaster numbers, historical communication records of pre-disaster numbers, and historical operation data of base stations;

[0007] Step 200, obtaining a first serial data stream based on the sorting of the comprehensive information of the disaster area numbers, the first serial data stream comprising Data units sorted by time, The data unit stores The first plane data generated by the comprehensive information of the disaster area number obtained at each moment;

[0008] Step 300, obtaining a second serial data stream based on the order of the historical communication data information of the number before the disaster, the second serial data stream includes Data units sorted by time, The data unit stores The historical communication data information of the number before the disaster obtained at each moment;

[0009] Step 400, input the first serial data stream and the second serial data stream into the number status recognition model, the number status recognition model includes a first backbone network, the first backbone network includes a first encoder, a second encoder, a third encoder, a first recognition fusion layer, a first fully connected layer, and a second fully connected layer; the first encoder inputs the first serial data stream, outputs the first recognition feature to the second encoder, the second encoder outputs the second recognition feature to the first recognition fusion layer, the first recognition fusion layer outputs the first recognition fusion feature to the first fully connected layer, and the first fully connected layer outputs the disaster area number status recognition result; the third encoder inputs the second serial data stream, outputs the third recognition feature to the first recognition fusion layer and the second fully connected layer, and the second fully connected layer outputs whether the pre-disaster number will be damaged in the disaster situation, and the damage is indicated by the pre-disaster number being unable to perform any communication in the disaster environment.

[0010] In a preferred embodiment, the disaster area number information includes: disaster area telephone equipment information, call records of the disaster area number, short message records of the disaster area number, and traffic usage of the disaster area number, which constitute a description text of the disaster area number information;

[0011] Telephone equipment information in the disaster area includes equipment type, equipment manufacturer, operating system and version;

[0012] Base station information includes: base station ID, base station geographic coordinates, base station basic parameters, number of concurrent connections of the base station, base station operation status consisting of base station information description text, the operation status includes working, partially damaged, and completely failed;

[0013] The disaster area user information includes: a description text of the disaster area user information consisting of user identity information and account information; the user identity information includes: user name, registered address, emergency contact; the account status is represented by the status of the account to which the phone number belongs, and the status is represented by arrears, suspended, or active;

[0014] The historical signal strength of the number before the disaster is expressed as the signal strength between the base station and the user's telephone equipment;

[0015] The pre-disaster number communication history records include: the time, duration, initiator and receiver of the number's historical calls and text messages;

[0016] The historical operation data of the base station includes: the operation status and performance indicators of the base station. The performance indicators include: call success rate, data throughput, and call delay.

[0017] In a preferred embodiment, the comprehensive information of the disaster area number and the historical communication data information of the number before the disaster are input into the number status recognition model after feature engineering. The comprehensive information of the disaster area number includes disaster area number information description text, base station information description text, and disaster area user information description text. The historical communication data information of the number before the disaster includes disaster area number historical communication description text. The disaster area number information description text, base station information description text, disaster area user information description text, and disaster area number historical communication description text are used through the WordEmbedding algorithm as a feature engineering method to generate disaster area number features, base station features, disaster area user features, and disaster area number historical communication features.

[0018] In a preferred embodiment, the first plane data includes a first face element for storing data, and a first face element indexes a data object. The first plane data also includes a relationship list for storing the association relationship between the data objects indexed by the first face element, and the element value of the i-th row and j-th column of the relationship list represents the quantitative value of the association relationship between the data objects indexed by the i-th and j-th first face elements; the association relationship includes high and low, which correspond to two quantitative values ​​respectively; the data objects include disaster area numbers, communication base stations, and disaster area users.

[0019] In a preferred embodiment, the data objects with a high correlation relationship are defined as: the number used by the user, the communication records between the numbers, and the number transmitting text messages or making calls through the base station.

[0020] In a preferred implementation, the disaster area number status identification result includes: the damage status of the disaster area number, the online status of the disaster area telephone equipment, and the signal status of the disaster area number.

[0021] In a preferred embodiment, the signal status is represented by five categories: excellent, good, general, poor, and severe. Excellent means that the normal communication quality is not affected; good means that the signal strength is significantly lost; general means that normal communication is possible only in areas with strong signals near the base station; poor means that all communications cannot be connected or communication is impossible after connection; severe means that the signal is completely lost and communication cannot be carried out.

[0022] In a preferred embodiment, the first recognition fusion layer is combined with the first fully connected layer for separate pre-training, and the training number status recognition model accurately identifies the status of the disaster area number based on the comprehensive information of the disaster area number.

[0023] In a preferred embodiment, the third encoder is pre-trained separately in combination with the second fully connected layer, and the trained number status recognition model can accurately determine whether the pre-disaster number will be damaged in a disaster situation based on the historical communication data information of the pre-disaster number.

[0024] The present invention provides a computer storage medium, which is used to store instructions that can be read by a computer. When the instructions stored in the medium are read, the aforementioned number status identification method based on information security can be executed.

[0025] The beneficial effects of the present invention are:

[0026] Accurate number status identification: This method combines the comprehensive information of disaster area numbers and pre-disaster communication history data to achieve accurate identification of number status. This method can identify which numbers can still maintain communication capabilities in disaster situations and which numbers may not work properly due to network damage or user terminal loss through multi-level feature extraction and fusion.

[0027] Improve the efficiency of disaster management and emergency response: By applying this number status identification method, relevant departments can quickly obtain an overview of the communication status of the disaster area and monitor and evaluate the affected user groups in real time. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] Figure 1 The present invention is a flowchart of a number status identification method based on information security. DETAILED DESCRIPTION

[0029] The subject matter described herein will now be discussed with reference to example implementations. It should be understood that the discussion of these implementations is only to enable those skilled in the art to better understand and implement the subject matter described herein, and the functions and arrangements of the elements discussed may be changed without departing from the scope of protection of the present specification. Various examples may omit, replace, or add various processes or components as needed. In addition, the features described in some examples may also be combined in other examples.

[0030] At least one embodiment of the present invention discloses a number status identification method based on information security, such as Figure 1 As shown, the following steps are included:

[0031] Step 100, obtaining comprehensive information of disaster area numbers, including: disaster area number information, base station information, and disaster area user information; obtaining historical communication data information of pre-disaster numbers, including: historical signal strength of pre-disaster numbers, historical communication records of pre-disaster numbers, and historical operation data of base stations;

[0032] In one embodiment of the present invention, the disaster area number information includes: a disaster area number information description text composed of the disaster area number, the disaster area phone equipment information, the call record of the disaster area number, the text message record of the disaster area number, and the traffic usage of the disaster area number;

[0033] Telephone equipment information in the disaster area includes equipment type, equipment manufacturer, operating system and version;

[0034] Base station information includes: base station ID, base station geographic coordinates, base station basic parameters, number of concurrent connections of the base station, base station operation status consisting of base station information description text, the operation status includes working, partially damaged, and completely failed;

[0035] The disaster area user information includes: a description text of the disaster area user information consisting of user identity information and account information; the user identity information includes: user name, registered address, emergency contact; the account status is represented by the status of the account to which the phone number belongs, and the status is represented by arrears, suspended, or active;

[0036] The pre-disaster number historical communication data information includes: pre-disaster number historical signal strength, pre-disaster number historical communication records, and historical base station operation data composed of the disaster area number historical communication description text;

[0037] The historical signal strength of the number before the disaster is expressed as the signal strength between the base station and the user's telephone equipment;

[0038] The pre-disaster number communication history records include: the time, duration, initiator and receiver numbers of the number's historical calls and text messages;

[0039] The historical operation data of the base station includes: the operation status and performance indicators of the base station. The performance indicators include: call success rate, data throughput, and call delay.

[0040] In one embodiment of the present invention, comprehensive information of disaster area numbers and historical communication data information of numbers before the disaster are input into a number status recognition model after feature engineering. The comprehensive information of disaster area numbers includes disaster area number information description text, base station information description text, and disaster area user information description text. The historical communication data information of numbers before the disaster includes disaster area number historical communication description text. The disaster area number information description text, base station information description text, disaster area user information description text, and disaster area number historical communication description text are used through the WordEmbedding algorithm as a feature engineering method to generate disaster area number features, base station features, user features, and disaster area number historical communication features.

[0041] Step 200, obtaining a first serial data stream based on the sorting of the comprehensive information of the disaster area numbers, the first serial data stream comprising Data units sorted by time, The data unit stores The first plane data generated by the comprehensive information of the disaster area number obtained at each moment;

[0042] The first plane data includes a first facet for storing data, wherein each first facet indexes a data object, and the first plane data also includes a relationship list for storing association relationships between the data objects indexed by the first facet, wherein the element value in the i-th row and j-th column of the relationship list represents a quantitative value of the association relationship between the data objects indexed by the i-th and j-th first facets;

[0043] The association relationships include high and low, corresponding to two quantitative values;

[0044] Data objects include disaster area numbers, communication base stations, and users in the disaster area;

[0045] The data objects with high correlation are defined as: the number used by the user, the communication records between numbers, and the number transmitting text messages or making calls through base stations;

[0046] Step 300, obtaining a second serial data stream based on the order of the historical communication data information of the number before the disaster, the second serial data stream includes Data units sorted by time, The data unit stores Historical communication data information of pre-disaster numbers obtained at each moment;

[0047] Step 400, input the first serial data stream and the second serial data stream into the number status recognition model, the number status recognition model includes a first backbone network, the first backbone network includes a first encoder, a second encoder, a third encoder, a first recognition fusion layer, a first fully connected layer, and a second fully connected layer; the first encoder inputs the first serial data stream, outputs the first recognition feature to the second encoder, the second encoder outputs the second recognition feature to the first recognition fusion layer, the first recognition fusion layer outputs the first recognition fusion feature to the first fully connected layer, and the first fully connected layer outputs the disaster area number status recognition result;

[0048] The third encoder inputs the second serial data stream, outputs the third identification feature to the first identification fusion layer and the second fully connected layer, and the second fully connected layer outputs whether the pre-disaster number will be damaged in the disaster situation.

[0049] In one embodiment of the present invention, the calculation formula of the first encoder is as follows:

[0050] ;

[0051] ;

[0052] in represents an aggregate representation of the v-th first bin of the L-th layer of the t-th data unit of the first serial data stream, and represent the bin feature of the vth first bin of the tth data unit of the first serial data stream of the Lth layer and the L-1th layer, respectively, represents a set of facets with a high correlation with the first facet v; Represents the universal quantifier symbol; Represents the bin feature of the uth first bin of the tth data unit of the first serial data stream of the L-1th layer, when L=1 , , The feature representation of the data object of the vth and uth first bin indexes of the tth data unit of the first serial data stream, the feature representation includes the disaster area number feature, the base station feature, and the disaster area user feature. When L=E is equal to a first identification feature of a vth first bin of a tth data unit of a first serial data stream; represents the aggregation function of layer L, such as average or maximum pooling function. represents the plane recognition weight matrix of the Lth layer, σ represents the Sigmoid function, Represents the concatenation function.

[0053] In one embodiment of the present invention, the calculation formula of the second encoder is as follows:

[0054] ;

[0055] in Indicates The second identifying feature, Indicates The second identifying feature, 1, represents the number of data units of the first serial data stream, , represents the set of all first bins of the t-th data unit of the first serial data stream, represents a first identification feature of the vth first bin of the tth data unit of the first serial data stream, and is the first and second serial recognition weight matrix, is the first serial identification bias parameter, and ReLU is the ReLU activation function.

[0056] In one embodiment of the present invention, the calculation formula of the third encoder is as follows:

[0057] ;

[0058] in Indicates A third identifying feature, Indicates A third identifying feature, 1, represents the number of data units of the second serial data stream, Indicates the second serial data stream data units, and is the third and fourth serial recognition weight matrix, is the second serial identification bias parameter, and ReLU is the ReLU activation function.

[0059] In one embodiment of the present invention, the calculation formula of the first recognition fusion layer is as follows:

[0060]

[0061] in, represents the combined features, represents the feature combination function (concatenation function or summation function), Indicates The second identifying feature, Indicates A third identifying feature.

[0062] In one embodiment of the present invention, the calculation formula of the first fully connected layer is as follows:

[0063] ;

[0064] in represents the first output matrix. The a-th column of the first row of the matrix represents the damaged state of the a-th disaster area number in the disaster-stricken area. 1 represents that the disaster area number is damaged, and 0 represents that the disaster area number is normal. Damaged means that the number cannot communicate at all. The b-th column of the second row of the matrix represents the online state of the b-th disaster area telephone device in the disaster-stricken area. 1 represents that the telephone device is online, and 0 represents that the telephone device is offline. The c-th column of the third row of the matrix represents the probability distribution of the signal state of the c-th disaster area number in the disaster-stricken area. represents the combined features, Indicates full connection.

[0065] In one embodiment of the present invention, the signal status is represented by five categories, namely excellent, good, general, poor, and severe. Excellent means that the normal communication quality is not affected; good means that the signal strength loss is obvious, such as communication in remote areas cannot be achieved due to the original weak signal and the small number of base stations; while the urban area has a strong signal and a large number of base stations and can communicate normally; general means that only the areas with strong signals near the base stations can communicate normally; poor means that all communications cannot be connected or communication is impossible after being connected; severe means that the signal is completely lost and communication cannot be carried out.

[0066] In one embodiment of the present invention, the calculation formula of the second fully connected layer is as follows:

[0067] ;

[0068] in represents the first output vector, and its fth component indicates whether the fth pre-disaster number will be damaged in the disaster situation. Damage is represented by 1, and no damage is represented by 0. Indicates A third identifying feature, Indicates full connection.

[0069] In one embodiment of the present invention, the first recognition fusion layer is combined with the first fully connected layer for separate pre-training, and the training number status recognition model accurately identifies the disaster area number status according to the comprehensive information of the disaster area number. The training loss function calculation formula is as follows:

[0070] ;

[0071] in represents the total loss, Indicates the number in the disaster area is damaged and identifies the loss. Indicates the online status identification loss of telephone equipment in the disaster area; Indicates the loss of signal status recognition of the number in the disaster area;

[0072] ;

[0073] in Indicates the number in the disaster area is damaged and identifies the loss. Indicates the total number of disaster area numbers, It is The real damage status label of the number in the disaster area, with a value of 0 or 1, 1 means the number is damaged, and 0 means the number is normal. is the first output matrix The damaged status labels of the disaster area numbers, It represents the logarithmic function with the natural constant e as the base;

[0074] ;

[0075] in Indicates the online status identification loss of telephone equipment in the disaster area, Indicates the total number of telephone devices in the disaster area, It is The real online status label of the telephone equipment in the disaster area, with a value of 0 or 1, 1 means the equipment is online, and 0 means the equipment is offline. is the first output matrix Online status tags for telephone devices in disaster areas, It represents the logarithmic function with the natural constant e as the base;

[0076] ;

[0077] in Indicates the loss of identification of the disaster area number signal status. M indicates the total number of disaster area number signal statuses. The default value of M is 5. Indicates the total number of disaster area numbers, It is The symbol value of the disaster area number, if the The actual signal status of the disaster area number is A signal state, its value is 1, otherwise it is 0. is the first output vector The disaster area number belongs to The probability of a signal state, Represents the logarithmic function with the natural constant e as the base.

[0078] In one embodiment of the present invention, the third encoder is pre-trained separately in combination with the second fully connected layer, and the training number status recognition model can accurately determine whether the pre-disaster number will be damaged in the disaster situation according to the historical communication data information of the pre-disaster number; the training loss function calculation formula is as follows:

[0079] ;

[0080] in Indicates loss, represents the total number of numbers before the disaster, It is indivual The actual damage result is 0 or 1, 1 means that the pre-disaster number will be damaged in the disaster situation, and 0 means that the pre-disaster number is normal in the disaster situation. is the first output vector A label that checks whether the pre-disaster number will be damaged in a disaster situation. Represents the logarithmic function with the natural constant e as the base.

[0081] The above describes an embodiment of the present invention, but this embodiment is not limited to the above-mentioned specific implementation mode. The above-mentioned specific implementation mode is merely illustrative and not restrictive. Under the guidance of this embodiment, ordinary technicians in this field can also make more forms of equivalent embodiments, all of which are within the protection of this embodiment.

Claims

1. A number status identification method based on information security, characterized in that: The following steps are involved: Step 100, obtaining comprehensive information of disaster area numbers, including: disaster area number information, base station information, and disaster area user information; obtaining historical communication data information of pre-disaster numbers, including: historical signal strength of pre-disaster numbers, historical communication records of pre-disaster numbers, and historical operation data of base stations; Step 200, obtaining a first serial data stream based on the sorting of the comprehensive information of the disaster area numbers, the first serial data stream comprising Data units sorted by time, The data unit stores The first plane data generated by the comprehensive information of the disaster area number obtained at each moment; Step 300, obtaining a second serial data stream based on the order of the historical communication data information of the number before the disaster, the second serial data stream includes Data units sorted by time, The data unit stores Historical communication data information of pre-disaster numbers obtained at each moment; Step 400, input the first serial data stream and the second serial data stream into the number status recognition model, the number status recognition model includes a first backbone network, the first backbone network includes a first encoder, a second encoder, a third encoder, a first recognition fusion layer, a first fully connected layer, and a second fully connected layer; the first encoder inputs the first serial data stream, outputs the first recognition feature to the second encoder, the second encoder outputs the second recognition feature to the first recognition fusion layer, the first recognition fusion layer outputs the first recognition fusion feature to the first fully connected layer, and the first fully connected layer outputs the disaster area number status recognition result; the third encoder inputs the second serial data stream, outputs the third recognition feature to the first recognition fusion layer and the second fully connected layer, and the second fully connected layer outputs whether the pre-disaster number will be damaged in the disaster situation, and the damage is indicated by the pre-disaster number being unable to perform any communication in the disaster environment.

2. A number status identification method based on information security according to claim 1, characterized in that: The disaster area number information includes: disaster area telephone equipment information, call records of the disaster area number, text message records of the disaster area number, and traffic usage of the disaster area number, which are composed of the disaster area number information description text; Telephone equipment information in the disaster area includes equipment type, equipment manufacturer, operating system and version; Base station information includes: base station ID, base station geographic coordinates, base station basic parameters, number of concurrent connections of the base station, base station operation status consisting of base station information description text, the operation status includes working, partially damaged, and completely failed; The disaster area user information includes: a description text of the disaster area user information consisting of user identity information and account information; the user identity information includes: user name, registered address, emergency contact; the account status is represented by the status of the account to which the phone number belongs, and the status is represented by arrears, suspended, or active; The historical signal strength of the number before the disaster is expressed as the signal strength between the base station and the user's telephone equipment; The pre-disaster number communication history records include: the time, duration, initiator and receiver of the number's historical calls and text messages; The historical operation data of the base station includes: the operation status and performance indicators of the base station. The performance indicators include: call success rate, data throughput, and call delay.

3. A method for identifying number status based on information security according to claim 1, characterized in that: The comprehensive information of the disaster area number and the historical communication data information of the number before the disaster are input into the number status recognition model after feature engineering. The comprehensive information of the disaster area number includes the disaster area number information description text, the base station information description text, and the disaster area user information description text. The historical communication data information of the number before the disaster includes the disaster area number historical communication description text. The disaster area number information description text, the base station information description text, the disaster area user information description text, and the disaster area number historical communication description text are used through the WordEmbedding algorithm as a feature engineering method to generate disaster area number features, base station features, disaster area user features, and disaster area number historical communication features.

4. A method for identifying number status based on information security according to claim 1, characterized in that: The first plane data includes a first facet element for storing data, and a first facet element indexes a data object. The first plane data also includes a relationship list for storing the association relationship between the data objects indexed by the first facet element, and the element value of the i-th row and j-th column of the relationship list represents the quantitative value of the association relationship between the data objects indexed by the i-th and j-th first facet elements; the association relationship includes high and low, which correspond to two quantitative values ​​respectively; the data objects include disaster area numbers, communication base stations, and disaster area users.

5. A method for identifying number status based on information security according to claim 4, characterized in that: Data objects with a high correlation are defined as: user usage of numbers, communication records between numbers, and numbers transmitting text messages or making calls through base stations.

6. A method for identifying number status based on information security according to claim 1, characterized in that: The results of the disaster area number status identification include: the damage status of the disaster area number, the online status of the disaster area telephone equipment, and the signal status of the disaster area number.

7. A method for identifying number status based on information security according to claim 6, characterized in that: The signal status is expressed in five categories: excellent, good, general, poor, and severe. Excellent means that it does not affect the normal communication quality; good means that the signal strength is significantly lost; general means that normal communication is possible only in areas with strong signals near the base station; poor means that all communications cannot be connected or communication is impossible after connection; severe means that the signal is completely lost and communication cannot be carried out.

8. A method for identifying number status based on information security according to claim 1, characterized in that: The first recognition fusion layer is combined with the first fully connected layer for separate pre-training, and the training number status recognition model accurately identifies the status of disaster area numbers based on the comprehensive information of disaster area numbers.

9. A method for identifying number status based on information security according to claim 1, characterized in that: The third encoder is pre-trained separately in combination with the second fully connected layer, and the training number status recognition model can accurately determine whether the pre-disaster number will be damaged in a disaster situation based on the historical communication data information of the pre-disaster number.

10. A computer storage medium, characterized in that: It is used to store instructions that can be read by a computer, and when the stored instructions are read, a number status identification method based on information security as described in any one of claims 1-9 can be executed.

Images