CN115438270B

CN115438270B - Intelligent recommendation method, device, equipment and storage medium for equipment information

Info

Publication number: CN115438270B
Application number: CN202211314991.1A
Authority: CN
Inventors: 周文明; 田志国; 沈世通; 陈军; 冯建设
Original assignee: CITIC Holdings Co Ltd; Shenzhen Xinrun Fulian Digital Technology Co Ltd
Current assignee: CITIC Holdings Co Ltd; Shenzhen Xinrun Fulian Digital Technology Co Ltd
Priority date: 2022-10-26
Filing date: 2022-10-26
Publication date: 2023-04-25
Anticipated expiration: 2042-10-26
Also published as: CN115438270A

Abstract

The application discloses an intelligent recommendation method, device, equipment and storage medium for equipment information, wherein the intelligent recommendation method for equipment information comprises the following steps: acquiring a user tag of a user of information to be recommended; determining recommendation equipment information of an information user to be recommended based on a user label and a preset label mapping relation; classifying the recommended equipment information, and transmitting the classified recommended equipment information batch to the user terminal; acquiring demand information of a user; and inputting the demand information and the recommended equipment information into a preset equipment information recommending model, and carrying out demand analysis processing on the demand information and the recommended equipment information based on the equipment information recommending model to obtain target equipment information. According to the method and the device, the recommended device information is automatically generated, the target device information is screened out according to the requirements, a user does not need to screen out and obtain the required device information in a large amount of data, the user terminal can quickly obtain the required device information, the device information acquisition efficiency is improved, and the user experience is improved.

Description

Intelligent recommendation method, device, equipment and storage medium for equipment information

Technical Field

The present disclosure relates to the field of computer information processing technologies, and in particular, to an intelligent recommendation method, apparatus, device, and storage medium for device information.

Background

With the development of the communication age, factories are gradually intelligent, and users can obtain required information only by searching in a data center.

However, along with the intellectualization of the equipment in the factory, the equipment information becomes diversified and diversified, and uses are different, under the condition of excessive transmission information, a user needs to screen a large amount of information to obtain required information, and in the process, a large amount of time is required to be spent, the efficiency of equipment information acquisition is low, and the user experience is poor.

Disclosure of Invention

The main purpose of the application is to provide a device information intelligent recommendation method, device, equipment and storage medium, and aims to solve the technical problem that in the prior art, the efficiency of obtaining device information is low, and user experience is poor.

In order to achieve the above object, the present application provides an intelligent recommendation method for device information, which includes:

acquiring a user tag of a user of information to be recommended;

determining recommendation equipment information of the information user to be recommended based on the user labels and a preset label mapping relation, wherein the label mapping relation is a mapping between each user label and corresponding recommendation equipment information;

Classifying the recommended equipment information, and transmitting classified recommended equipment information batches to a user terminal;

acquiring demand information of a user;

inputting the demand information and the recommended equipment information into a preset equipment information recommendation model, and carrying out demand analysis processing on the demand information and the recommended equipment information based on the equipment information recommendation model to obtain target equipment information.

Optionally, before the step of acquiring the user tag of the information user to be recommended, the method includes:

acquiring user information and equipment information in an Internet of things platform;

calibrating the user information to corresponding user labels;

determining recommended equipment information corresponding to the user tag based on the equipment information;

and establishing a mapping relation between each user tag and the corresponding recommendation equipment information to obtain a tag mapping relation.

Optionally, the step of determining recommended device information corresponding to the user information based on the device information includes:

determining a first feature vector of the device information and a second feature vector of the user information;

calculating the feature distance of the first feature vector and the second feature vector;

And determining the equipment information with the characteristic distance smaller than a preset distance threshold value as recommended equipment information of the corresponding user tag.

Optionally, the step of classifying the recommendation device information and transmitting the classified recommendation device information batch to the user terminal includes:

classifying the recommended equipment information based on a category label of preset equipment information to obtain recommended equipment information of a plurality of category sets;

determining the transmission priority of the recommended equipment information of each category set;

based on the transmission priority, carrying out data arrangement on the recommendation equipment information of the class sets to obtain arranged recommendation equipment information;

and transmitting the arranged recommended equipment information batch to a user terminal based on a preset batch transmission rule.

Optionally, before the step of inputting the requirement information and the recommended device information into a preset device information recommendation model and performing requirement analysis processing on the requirement information and the recommended device information based on the device information recommendation model to obtain target device information, the method includes:

analyzing the information of the recommending equipment into a target file in a preset format;

And determining a corresponding information matrix of the target file.

Optionally, the step of determining the corresponding information matrix of the target file includes:

partitioning the target file based on a preset information partitioning rule to obtain a block of the target file;

determining information units in the block and coordinate information of the information units;

and carrying out vectorization processing on the information units and the coordinate information of the information units, and forming an information matrix corresponding to the target file by the vectorized information units and the coordinate information of the information units.

Optionally, before the step of obtaining the requirement information of the user, the method includes:

acquiring a device information set, required information training data and a device information label of the required information training data;

and performing iterative training on a preset model to be trained based on the equipment information set, the required information training data and the equipment information label of the required information training data to obtain an equipment information recommendation model meeting the accuracy condition.

The application also provides an equipment information intelligent recommendation device, the equipment information intelligent recommendation device includes:

The label acquisition module is used for acquiring a user label of the information user to be recommended;

the determining module is used for determining the recommended equipment information of the information user to be recommended based on the user labels and a preset label mapping relation, wherein the label mapping relation is the mapping between each user label and the corresponding recommended equipment information;

the transmission module is used for classifying the recommended equipment information and transmitting the classified recommended equipment information batch to the user terminal;

the demand information acquisition module is used for acquiring demand information of a user;

the analysis module is used for inputting the requirement information and the recommended equipment information into a preset equipment information recommendation model, and carrying out requirement analysis processing on the requirement information and the recommended equipment information based on the equipment information recommendation model to obtain target equipment information.

The application also provides an intelligent recommendation device for device information, which comprises: a memory, a processor and a program stored on the memory for implementing the device information intelligent recommendation method,

the memory is used for storing a program for realizing the intelligent recommendation method of the equipment information;

The processor is used for executing a program for realizing the intelligent recommendation method of the equipment information so as to realize the steps of the intelligent recommendation method of the equipment information.

The application also provides a storage medium, wherein the storage medium stores a program for realizing the intelligent device information recommendation method, and the program for realizing the intelligent device information recommendation method is executed by a processor to realize the steps of the intelligent device information recommendation method.

Compared with the prior art that the efficiency of equipment information acquisition by users is low, the equipment information intelligent recommending method, device, equipment and storage medium provided by the application are poor in user experience, and in the application, the user label of the information user to be recommended is acquired; determining recommendation equipment information of the information user to be recommended based on the user labels and a preset label mapping relation, wherein the label mapping relation is a mapping between each user label and corresponding recommendation equipment information; classifying the recommended equipment information, and transmitting classified recommended equipment information batches to a user terminal; acquiring demand information of a user; inputting the demand information and the recommended equipment information into a preset equipment information recommendation model, and carrying out demand analysis processing on the demand information and the recommended equipment information based on the equipment information recommendation model to obtain target equipment information. In the method, the recommended equipment information of the information user to be recommended is generated through the mapping relation between each user label and the corresponding recommended equipment information, the generated recommended equipment information is classified and transmitted to the user terminal in batches, the target equipment information is rapidly screened out according to the specific requirements of the equipment information of the user, the user does not need to screen out a large amount of data of an Internet of things platform or a data platform to obtain the required equipment information, the user rapidly obtains the required equipment information at the terminal, the equipment information obtaining efficiency is improved, and the experience of the user is improved.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the application and together with the description, serve to explain the principles of the application. In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings that are required to be used in the description of the embodiments or the prior art will be briefly described below, and it will be obvious to those skilled in the art that other drawings can be obtained from these drawings without inventive effort.

FIG. 1 is a schematic diagram of a device architecture of a hardware operating environment according to an embodiment of the present application;

FIG. 2 is a schematic flow chart of a first embodiment of an intelligent recommendation method for device information in the present application;

FIG. 3 is a schematic system flow chart of a second embodiment of an intelligent recommendation method for device information in the present application;

fig. 4 is a schematic diagram of a classification module of a first embodiment of an intelligent recommendation method for device information in the present application.

The realization, functional characteristics and advantages of the present application will be further described with reference to the embodiments, referring to the attached drawings.

Detailed Description

It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the present application.

As shown in fig. 1, fig. 1 is a schematic diagram of a terminal structure of a hardware running environment according to an embodiment of the present application.

The terminal in the embodiment of the application may be a PC, or may be a mobile terminal device with a display function, such as a smart phone, a tablet computer, an electronic book reader, an MP3 (Moving Picture Experts Group Audio Layer III, dynamic image expert compression standard audio layer 3) player, an MP4 (Moving Picture Experts Group Audio Layer IV, dynamic image expert compression standard audio layer 4) player, a portable computer, or the like.

As shown in fig. 1, the terminal may include: a processor 1001, such as a CPU, a network interface 1004, a user interface 1003, a memory 1005, a communication bus 1002. Wherein the communication bus 1002 is used to enable connected communication between these components. The user interface 1003 may include a Display, an input unit such as a Keyboard (Keyboard), and the optional user interface 1003 may further include a standard wired interface, a wireless interface. The network interface 1004 may optionally include a standard wired interface, a wireless interface (e.g., WI-FI interface). The memory 1005 may be a high-speed RAM memory or a stable memory (non-volatile memory), such as a disk memory. The memory 1005 may also optionally be a storage device separate from the processor 1001 described above.

Optionally, the terminal may also include a camera, an RF (Radio Frequency) circuit, a sensor, an audio circuit, a WiFi module, and so on. Among other sensors, such as light sensors, motion sensors, and other sensors. Specifically, the light sensor may include an ambient light sensor that may adjust the brightness of the display screen according to the brightness of ambient light, and a proximity sensor that may turn off the display screen and/or the backlight when the mobile terminal moves to the ear. As one of the motion sensors, the gravity acceleration sensor can detect the acceleration in all directions (generally three axes), and can detect the gravity and the direction when the mobile terminal is stationary, and the mobile terminal can be used for recognizing the gesture of the mobile terminal (such as horizontal and vertical screen switching, related games, magnetometer gesture calibration), vibration recognition related functions (such as pedometer and knocking), and the like; of course, the mobile terminal may also be configured with other sensors such as a gyroscope, a barometer, a hygrometer, a thermometer, an infrared sensor, and the like, which are not described herein.

It will be appreciated by those skilled in the art that the terminal structure shown in fig. 1 is not limiting of the terminal and may include more or fewer components than shown, or may combine certain components, or a different arrangement of components.

As shown in fig. 1, an operation device, a network communication module, a user interface module, and an apparatus information intelligent recommendation program may be included in a memory 1005 as one type of computer storage medium.

In the terminal shown in fig. 1, the network interface 1004 is mainly used for connecting to a background server and performing data communication with the background server; the user interface 1003 is mainly used for connecting a client (user side) and performing data communication with the client; and the processor 1001 may be used to invoke the device information intelligent recommendation program stored in the memory 1005.

Referring to fig. 2, an embodiment of the present application provides an apparatus information intelligent recommendation method, where the apparatus information intelligent recommendation method includes:

step S100, obtaining a user tag of a user to be recommended information;

step S200, determining the recommended equipment information of the information user to be recommended based on the user labels and a preset label mapping relation, wherein the label mapping relation is the mapping between each user label and the corresponding recommended equipment information;

step S300, classifying the recommended equipment information, and transmitting the classified recommended equipment information batch to a user terminal;

step S400, obtaining requirement information of a user;

And S500, inputting the requirement information and the recommended equipment information into a preset equipment information recommendation model, and carrying out requirement analysis processing on the requirement information and the recommended equipment information based on the equipment information recommendation model to obtain target equipment information.

In this embodiment, a specific application scenario may be:

along with the intellectualization of the equipment in the factory, the equipment information becomes diversified and diversified, and uses are different, under the condition of excessive transmission information, a user needs to screen a large amount of information to obtain required information, a large amount of time is required to be spent in the process, the efficiency of equipment information acquisition is low, and the user experience is poor.

The method comprises the following specific steps:

step S100, obtaining a user tag of a user to be recommended information;

in this embodiment, the device information intelligent recommendation method is applied to a device information intelligent recommendation apparatus.

In this embodiment, the information user to be recommended is a user who needs to view equipment information in the internet of things platform, the user tag of the information user to be recommended is a user tag corresponding to the user information in the internet of things platform of the report user to be recommended, the user tag is generated according to the user information, the user information includes information such as a user name, a position, task allocation, etc., for example, the user information includes information such as a user a position as a detection engineer, and the corresponding user tag includes machine detection, function detection, etc., and the device recommends corresponding equipment information according to the corresponding user tag.

In this embodiment, the means for obtaining the user tag of the information user to be recommended may be that the device obtains the tag of the corresponding user sent in the database of the internet of things platform after the information user to be recommended logs in the interactive interface of the internet of things platform; the user can upload the user tag to the device by the user to be recommended, for example, the user A registers an A account in an internet of things platform of an X factory, the internet of things platform stores user information of the A account, when the user A logs in the intelligent recommending device for the equipment information, the user information of the user A of the internet of things platform is sent to the device, and the device marks the user A with an M tag and an N tag according to the user information.

Before the step S100, the step of acquiring the user tag of the information user to be recommended, the method includes the following steps a100-a400:

step A100, obtaining user information and equipment information in an Internet of things platform;

in this embodiment, the internet of things platform is an integrated platform integrating the capabilities of device management, data security communication, message subscription, and the like. Downward supporting connection of mass equipment, and collecting equipment data to cloud; the cloud end API is provided upwards, and the server side can send the instruction to the equipment side by calling the cloud end API, so that remote control is realized. The device is in communication connection with the Internet of things platform, the device acquires the user information and the device information in the Internet of things platform, which are sent by the Internet of things platform, wherein the user information comprises information such as user names, positions and task allocation, and the device information comprises operation data, energy consumption data, visual data and the like of each device.

Step A200, calibrating the corresponding user labels with the user information;

in this embodiment, the device marks the user information with a corresponding user tag, that is, marks each user with a corresponding user tag according to the user information of each user, for example, the user information includes a user a position as a detection engineer, and the task allocation range is a punching machine, where the corresponding user tag includes punching machine detection, function detection of the punching machine, and the like.

In this embodiment, if the user information is modified or updated, the apparatus generates a corresponding updated user tag according to the modified or updated user information, and generates corresponding updated recommendation device information according to the updated user tag.

Step A300, based on the device information, determining recommended device information corresponding to the user tag;

in this embodiment, the apparatus determines the recommended device information corresponding to the user tag based on the device information, and since the device information includes a large amount of information, the recommended device information is the recommended device information corresponding to each user tag, for example, the tag of the user a includes a punch detection, a function detection of the punch, and the recommended device information of the apparatus for the user a includes operation data of the punch, energy consumption data of the punch, and visual data of the punch.

Specifically, the step A300 includes the following steps A310-A330:

step A310, determining a first feature vector of the device information and a second feature vector of the user information;

in this embodiment, the device determines the first feature vector of the device information and the second feature vector of the user information, and the device determines the first feature vector of the device information and the second feature vector of the user information by adopting a corresponding feature extraction method according to information properties of the device information and the user information, if the device information and the user information are image information, an image feature extraction method is adopted, and if the device information and the user information are text information, a text feature extraction method is adopted.

Step A320, calculating feature distances of the first feature vector and the second feature vector;

in this embodiment, the device calculates the feature distances of the first feature vector and the second feature vector, and calculates the feature distance of each feature vector in the first feature vector and each feature vector in the second feature vector in a recursive manner, for example, the first feature vector includes A1 and A2, the second feature vector includes A1, A2 and a3, and then calculates the feature distances of A1 and B1, B2 and B3, and the feature distances of A2 and B1, B2 and B3, respectively, to obtain 6 feature distance results.

And step A330, determining the equipment information with the characteristic distance smaller than a preset distance threshold value as recommended equipment information of the corresponding user tag.

In this embodiment, the device determines the equipment information with the feature distance smaller than the preset distance threshold as recommended equipment information of the corresponding user tag, where the distance threshold is a self-set threshold range, and if the feature distance is smaller than the preset distance threshold, the equipment information accords with the current user tag, and the feature distance obtained by determining the recommended equipment information as the user tag, for example, the feature distance obtained by the second feature vector of the user information of the user a and the first feature vector of the equipment information includes X1, X2, X3, X4, and X5, where X1 and X3 are smaller than the preset distance threshold, and the recommended equipment information corresponding to the user tag of the user a is the equipment information corresponding to X1 and X3.

And step A400, establishing a mapping relation between each user label and the corresponding recommendation equipment information to obtain a label mapping relation.

In this embodiment, the device establishes a mapping relationship between each user tag and the corresponding recommended device information to obtain a tag mapping relationship, and the device establishes a mapping relationship between each user tag and the corresponding recommended device information by matching each user tag with the corresponding recommended device information to establish a mapping relationship between the user tag and the recommended device information.

in this embodiment, the label mapping relationship includes a mapping between each user label and corresponding recommendation device information, and the apparatus obtains recommendation device information corresponding to the user label based on the user label and a preset label mapping relationship, for example, the user label of the user a includes X1 and X2, and the label mapping relationship X1 maps the recommendation device information Y1 and X2 maps the recommendation device information Y2, so that the recommendation device information of the information user to be recommended is Y1 and Y2.

In this embodiment, through the mapping relationship between each user tag and the corresponding recommended device information, the recommended device information of the information user to be recommended is generated, and the generated recommended device information is classified and transmitted to the user terminal in batches, so that the user does not need to screen and obtain the required device information in a large amount of data of the internet of things platform or the data platform, the device information acquisition efficiency is improved, and the experience of the user is improved.

After the step of determining the recommended device information of the information user to be recommended based on the user tag and the preset tag mapping relationship in the step S200, the method includes the following steps B100-B300:

step B100, encrypting the recommendation equipment information to obtain encrypted recommendation equipment information;

in this embodiment, specifically, the method for encrypting the recommendation device information by the apparatus is as follows: firstly, generating a spectrogram through an import scale library, then sampling voice preset by a user, performing FFT conversion on the voice preset by the user so as to convert the voice signal into a region graph of an original voice signal, then converting a decimal system into a binary system, performing iteration for times after conversion, wherein the times are preset times, and performing voice encryption in the mode.

Step B200, obtaining a verification signal;

in this embodiment, the verification signal is a user signal received by the terminal, and is used to verify the identity of the user.

And step B300, decrypting the encrypted recommended equipment information based on the verification signal.

In this embodiment, encryption is performed when data transmission is performed on the computer end and the mobile phone end, and when data information to be transmitted is transmitted to the mobile end or the computer end, the data information to be transmitted is opened in a corresponding manner.

In the embodiment, the recommendation equipment information is encrypted, verified and decrypted, and a outsider is placed to acquire the recommendation equipment information through the information of the login user, so that the safety of the information is improved, and the experience of the user is improved.

Specifically, the step B300 includes the following steps B310-B330:

step B310, segmenting the voice verification signal to obtain a segmented voice verification signal;

step B320, constructing a preset number of encryption matrixes based on the segmented voice verification signals;

and step B330, decrypting the encrypted recommended device information based on the encryption matrix.

In this embodiment, the decryption method is as follows: dividing the voice verification signal of each frame into P segments:

where T is the length of the segment and K is the frame pointer, in the algorithm for generating the key signal, since parameters P and T are necessary, they will be inserted intoIn a header of encrypted voice data transmitted in a defined format, the indivisible part can be separated by constructing a matrix Ae of underdetermined mixing ratio, so that the original part is separated,

p is a full order array of P, pseudo-randomly producing a uniform distribution between-1 and 1,

Is a standard value of the quantity,

the original speech can be well stripped, then a P.2P-dimensional underdetermined encryption matrix is constructed by utilizing Kronecker (matrix convolution) to form a matrix A, the secret matrix is also used as a part of the secret key, another form of P.2P-dimensional underdetermined secret matrix can be constructed,

wherein B is a full order matrix of dimension P, generated from pseudo-random numbers distributed uniformly between (-1, 1), C is a matrix of dimension 1*2, and is also critical for the choice of matrices B and C, but is not only known for key signals for attack

A matrix C is also required to prevent the key from being hacked, thereby improving the security of the key.

After the step of determining the recommended device information of the information user to be recommended based on the user tag and the preset tag mapping relationship in the step S200, the method further includes the following steps C100-C300:

step C100, determining the frequency range of the data signal of the recommended equipment information;

step C200, filtering signals outside the frequency range of the signals to obtain recommendation equipment information after the signals are filtered;

in this embodiment, the device uses a filter to reject redundant frequencies, and the filter can effectively filter frequency points with specific frequencies or frequencies other than the frequency points in the power line to obtain a power signal with specific frequencies, or eliminate a power signal with specific frequencies, so as to reduce the working content of the information receiving end, improve the information transmission efficiency, enable a user to quickly obtain required equipment information at the terminal, improve the equipment information acquisition efficiency, and improve the experience of the user.

And step S300, classifying the recommended equipment information, and transmitting the classified recommended equipment information batch to a user terminal.

In this embodiment, since there is also a possibility that a large amount of information is stored in the recommended device information, in order to further improve the efficiency of sending information to the user terminal, the device classifies the recommended device information, and transmits the classified recommended device information to the user terminal in batches, so that the transmission speed is prevented from being too slow due to too large data, thereby improving the efficiency of sending information to the user terminal, improving the efficiency of obtaining device information, and improving the experience of the user.

Specifically, the step S300 includes the following steps S310 to S340:

step S310, classifying the recommended equipment information based on a category label of preset equipment information to obtain recommended equipment information of a plurality of category sets;

in this embodiment, the apparatus classifies the recommended device information based on a preset class label of the device information to obtain recommended device information of a plurality of class sets, for example, the recommended device information includes A1, A2, A3, and A4, where the class labels of A1 and A2 are device energy consumption data, the class label of A3 is device visual data, and the class label of A4 is device operation data.

In this embodiment, the device classifies the same type of data and sequentially arranges the same type of data to obtain the classified data, where the types include a user type and a data type. For example, in a factory, data types are classified into equipment, energy consumption and vision, a device classifies the data to be transmitted, and the equipment, energy consumption and vision data in the data to be transmitted are correspondingly classified.

In another embodiment, determining a sequence number of a data packet in the recommended device information; and forwarding the first data packet in the data to be transmitted based on the serial number of the data packet, detecting the later data packet, and discarding the data packet which is the same as the first data packet in the later data packet to obtain screened data.

Step S320, determining the transmission priority of the recommended equipment information of each category set;

in this embodiment, the device determines the transmission priority of the recommended device information according to the user information, and defines four dimensions of the feedback information, and evaluates importance, urgency, user tendency, technical process easiness and the like.

Step S330, based on the transmission priority, data arrangement is carried out on the recommendation equipment information of the class sets to obtain the arranged recommendation equipment information;

in the embodiment, the numerical value comprehensive comparison is performed, the numerical value summary is low, and the high priority processing is represented; the total value is representative of low priority processing. And carrying out data arrangement on the recommended equipment information of the class sets, preventing data from crossing, and improving the data transmission efficiency.

Step S340, transmitting the arranged recommended device information batch to the user terminal based on a preset batch transmission rule.

In this embodiment, the apparatus transmits the arranged recommended device information to the user terminal in batches based on a preset batch transmission rule, where the batch transmission rule includes dividing the recommended device information of each category set into transmission batches according to categories and data packet sizes, for example, the arranged recommended device information includes A1, A2, B1, B2, and C3, where the data packet sizes are 3M, 2M, 4M, 5M, and 10M, the categories A1 and A2 are device operation data, B1 and B2 are device energy consumption data, C3 is device vision data, a preset data size threshold is 5M, the transmission batches are A1 and A2 are a first batch, B1 is a second batch, B2 is a third batch, and C3 is a fourth batch.

In this embodiment, the apparatus divides batches according to the recommended device information and the size of the data packet, that is, the device information is classified, after the device information is classified, part of the classified data is sequentially and directly transmitted, and unclassified data is transmitted after waiting for the classification, a timer is added therein, if the waiting time for the classification exceeds the time threshold of the timer, unclassified data is input into the database of error reporting data, error reporting content is imported into the error feedback port, then the error feedback port transmits the data to the feedback information analysis end, the feedback information analysis end analyzes the feedback of each user, and the feedback information analysis end firstly prioritizes the feedback of the user. For error reporting data, a developer regularly checks the error reporting data, and if the error reporting data is missing due to the data category label, the error reporting data is marked with a corresponding category label; if new category data exists, a corresponding category label is established.

Step S400, obtaining requirement information of a user;

in this embodiment, the requirement information is specific information required by the user at a certain place in the recommended device information after the recommended device information is received by the terminal, for example, the requirement of the user is "energy consumption data of the punch".

In this embodiment, first, the requirement information of the user is acquired, where the manner in which the device acquires the requirement information of the user may be:

mode one: if the voice command is detected, extracting voice information in the voice command, and analyzing the voice information to obtain target demand information;

mode two: in this embodiment, an inquiry interface may be further provided, and the target demand information may be acquired based on the information input on the inquiry interface.

In this embodiment, in the query interface, corresponding requirement information is output, and the requirement information may be one or more.

The step S400, before the step of obtaining the requirement information of the user, includes the following steps D100-D200:

step D100, acquiring a device information set, required information training data and a device information label of the required information training data;

in this embodiment, the device information set includes a large amount of device information, which may be all device information in a factory range or all device information in a certain area range; the demand information training data is data of user demand information for training, and the demand information training data can be words or voices; the equipment information label of the demand information training data is a label of equipment information corresponding to the demand information.

And step D200, performing iterative training on a preset model to be trained based on the equipment information set, the required information training data and the equipment information labels of the required information training data to obtain an equipment information recommendation model meeting the accuracy condition.

In this embodiment, the device performs iterative training on a preset model to be trained based on the equipment information set, the demand information training data and the equipment information label of the demand information training data to obtain an equipment information recommendation model meeting accuracy conditions, and the equipment information recommendation model obtained through the training process of the big data model can quickly and accurately find corresponding equipment information in the equipment information set according to the demand information of the user, so that the equipment information acquisition efficiency is improved, and the experience of the user is improved. It should be noted that, if the user receives the recommended device information at the terminal, and does not need to perform further device information, the required information is absent, and the obtained target information is absent.

Specifically, the step D200 includes the following steps D210-D240:

step D210, inputting the demand information and the training data of the equipment information set into the preset model to be trained to obtain the predicted equipment information in the equipment information set;

step D220, performing difference calculation on the predicted equipment information and the equipment information label of the demand information training data to obtain an error result;

step D230, judging whether the error result meets an error standard indicated by a preset error threshold range or not based on the error result;

and step D240, if the error result does not meet the error standard indicated by the preset error threshold range, returning to the step of inputting the demand information and the training data of the equipment information set into the preset model to be trained to obtain the predicted equipment information in the equipment information set, and stopping training until the training error result meets the error standard indicated by the preset error threshold range to obtain the delay time prediction model.

In the step S500, the requirement information and the recommended device information are input into a preset device information recommendation model, and based on the device information recommendation model, requirement analysis processing is performed on the requirement information and the recommended device information, and before the step of obtaining target device information, the method includes the following steps E100-E200:

Step E100, analyzing the information of the recommended equipment into a target file in a preset format;

in this embodiment, the device parses the recommendation device information into a target file in a preset format, specifically, the device parses the recommendation device information into a target file in a preset format through open source software, for example, the recommendation device information is a file in a PDF format, that is, the parsing result of each page of content of the PDF is output in Json format, where each page of the PDF may be one Json data, the logical structure of the Json includes blocks (blocks) composed of a plurality of lines, each line is composed of a plurality of lines, one line may be represented by using a dictionary, the keys of the dictionary are composed of dir (direction of text blocks), spans (small blocks or unit units), each spans are composed of a plurality of spans, that is, the spans are the smallest expression units or unit units, where spans have size, font size, color, text, font coordinates, and the like.

And E200, determining a corresponding information matrix of the target file.

In this embodiment, the device determines an information matrix corresponding to the target file, where the information matrix finally includes information of each recommended device, so that the model can find the corresponding target device information in the information matrix according to the requirement information.

Specifically, the step E200 includes the following steps E210-E230:

step E210, partitioning the target file based on a preset information partitioning rule to obtain a block of the target file;

in this embodiment, the apparatus performs partition processing on the target file based on a preset information partition rule to obtain a block of the target file, specifically, the type of the target file is a text type, a content corresponding to a paragraph in a certain page text in a PDF is used as a block according to the preset information partition rule, the partition processing is performed on the target file, if the type of the target file is a table type, a large table unit or a region unit in a certain table in the PDF is subjected to partition processing according to the preset table partition rule, and each block of the target file in json format is obtained.

Step E220, determining information units in the block and coordinate information of the information units;

in this embodiment, the apparatus determines the information units in the block and the coordinate information of the information units, specifically, uses a section of text or a table or a section of video including but not limited to a section of text or a section of table or a section of video in the block of the target file as an information unit, and records the coordinate information of the information units in the block, so that the model can find the corresponding target device information in the information matrix according to the requirement information.

And E230, vectorizing the information units and the coordinate information of the information units, and forming a corresponding information matrix of the target file by the vectorized information units and the coordinate information of the information units.

In this embodiment, the device performs vectorization processing on the information unit and the coordinate information of the information unit, and forms the vectorized information unit and the coordinate information of the information unit into the information matrix corresponding to the target file.

In this embodiment, the device inputs the requirement information and the recommended device information into a preset device information recommendation model, performs requirement analysis processing on the requirement information and the recommended device information based on the device information recommendation model to obtain target device information, and obtains the device information recommendation model through the training process of the big data model.

In another embodiment, the device is provided with an error feedback port, error reporting contents and opinion feedback contents in the computer end and the mobile end are imported into the error feedback port, the error feedback port sends data to the device for feedback information analysis, the device analyzes feedback of each user, and the feedback information analysis end firstly prioritizes the feedback of the user. Firstly, a first step, data push errors are a first sequence, the priority level is high, and a numerical value 1 is defined; the partial error of the data content is a second sequence, a first value of 2; user feedback is a third sequence, defining a value of 3; secondly, defining four dimensions of feedback information, namely evaluating importance, urgency, problem solving benefit and technical processing realizability, wherein a first sequence of each dimension represents a high priority level, and a numerical value of 1 is defined; the second sequence represents the priority level in the middle, and a value of 2 is defined; the third sequence represents a low priority level, defining a value of 3;

to sum up, the numerical summary is compared, the numerical summary is low, and the high priority processing is represented; the total value is representative of low priority processing.

Specifically, the first sequence processing: after receiving the problem of the first sequence, the feedback information analysis end imports the information into the information receiving module and imports the user information into the information receiving module together, then the information receiving module reissues the instruction to enable the information extraction system to extract information required by the user from the database of the Internet of things again according to the information subscribed by the user, and then the information is packaged and sent together with the next batch of data through the steps;

Second sequence processing: comparing partial errors with original data, searching corresponding data in a database, and adding all the front part and the rear part into repair data to ensure that the continuity of the data is convenient for a user to check;

third sequence processing: the user feedback is directly displayed through the feedback information analysis end, and the manager directly checks the user feedback and modifies more feedback.

Based on the first embodiment, the present application further provides another embodiment, referring to fig. 3, the device information intelligent recommendation apparatus includes: the system comprises an Internet of things information database, an information extraction system, an information classification module, a network information reference module, an encryption terminal, a sending module, a first server, a second server, a mobile terminal, a computer terminal, an error feedback terminal and a feedback information analysis terminal. The internet of things information base is used for storing required data and classifying and storing the required data; the information extraction system is used for extracting internal data of the information base of the Internet of things; the information analysis module is used for classifying the collected information and comparing the information, and the network information reference module is connected with the information classification module and used as one of comparison reference objects; the encryption terminal is used for encrypting the classified data information; the sending module is used for sending the information in the encrypted terminal; the first server is used for receiving information from the sending module; the second server is used for helping the first server to process data when the load of the first server is excessive, and meanwhile, the function of the second server is the same as that of the first server; the computer end and the mobile end are communication data demand ends; the error feedback port is used for the port for the feedback of the data problem found by the computer end and the mobile end; the feedback information analysis end is used for specifically analyzing the feedback problem and then guiding the feedback problem into the information classification module.

Specifically, referring to fig. 4, the information classification module includes a data receiving module, a data analysis module, an information data arrangement module, a data type presetting module, and a comparison model establishing module, where the data receiving is to receive information in the information receiving module, the data analysis module is to analyze types of data in the data receiving module, the data type presetting is to store user information and push data according to requirements of users, the comparison model establishing is to re-cooperate data in the data type presetting to establish a data model and reduce data required by users, and the information data arrangement module is to classify users of the same data type according to the user and the data type, and sequentially arrange the users.

Specifically, the method corresponding to the intelligent equipment information recommending device comprises the following steps:

user subscription information;

user information and extraction of internet of things data: firstly, the information base of the Internet of things is used for storing required data and classifying the required data, then the information extraction system is used for extracting data in the information base of the Internet of things, the information classification module classifies the collected information and compares the information, and the information receiving module receives the data from the information extraction system and transmits the data to the information classification module;

Data comparison: the data receiving is to receive the information in the information receiving module, the data analyzing module is to analyze the type of the data in the data receiving module, the data type is preset to store the user information and push the data according to the requirement of the user, the comparison model is established to build the data model by matching the data in the data type preset with the data analyzing module and reduce the data required by the user, meanwhile, the network information reference module is used as a reference object for the information classifying module, the data analyzing module in the information classifying module is firstly used for data reduction through the comparison model, meanwhile, the network information reference module is used as a secondary reference object, if the overlapping degree of the information content and the network is found to be too high, the reduced content is reduced in the data analyzing module, the information data arranging module is used for classifying the users with the same data type according to the user and the data type, and the users with the same data type are orderly arranged;

and (3) data transmission: after data processing is carried out through the information analysis module, data encryption is carried out through the encryption terminal, the encrypted data are transmitted to the transmission module, and the encrypted data are transmitted to the first server through the transmission module;

And (3) data processing: firstly, receiving information from a sending module through an information receiving end, then removing redundant frequencies through a filter, effectively filtering frequency points with specific frequencies or frequencies outside the frequency points in a power line by the filter to obtain a power signal with specific frequencies, or eliminating an electric 0 source signal with specific frequencies, reducing working contents of the information receiving end, analyzing encrypted data by a decoding terminal, comparing decrypted data by an information arrangement module, preventing data crossing in the process of data analysis, determining by the information arrangement module, and if crossing conditions occur, sequencing the data again, wherein an information arrangement encryption module encrypts data according to a single user:

subscription information encryption: the information arrangement encryption module is set according to a password added by a user, the password is voice encryption, a spectrogram is firstly generated through an import scale.io.wavfile library, then voice is sampled, the sampling frequency is 8000, 2048-point FFT conversion is carried out on a voice signal so as to convert the voice signal into a region graph of an original voice signal, then the voice signal is converted into binary from decimal, after conversion, iteration is carried out for times, the time interval is 80-90, and voice encryption is carried out in the mode;

Subscription information transmission: all the subscription information is sent to a mobile terminal or a computer terminal through a batch sending terminal after encryption, and then the subscription content is unlocked through a voice decryption mode;

error feedback: the error reporting content and the opinion feedback content in the computer end and the mobile end are imported into an error feedback port, then the error feedback port sends data to a feedback information analysis end, the feedback information analysis end analyzes the feedback of each user, and the feedback information analysis end firstly prioritizes the feedback of the user.

In this embodiment, the data is analyzed, then arranged, specific distinction is performed according to the data type and the user group, then the data after the distinction is directly packaged and encrypted in the distinguishing process, the data is sequentially transmitted by using the sending module, then the server receives the data, the frequencies except the data are filtered by the filter, and the working efficiency of the information receiving end is increased, namely, a part of the data is directly transmitted after the classification is finished, and the data which is not classified can be transmitted after waiting for the classification is finished, so that the transmission efficiency is effectively increased;

And the user subscription data is encrypted through the information arrangement encryption module, then the encrypted user subscription data is sent to the computer end and the mobile end through the information batch sending module, and then the user subscription data is unlocked through the voice wavelength, so that the privacy of the user is ensured.

And feedback is classified by setting an error feedback port and a feedback information analysis end, so that the efficiency of error processing is improved.

Optionally, the device information intelligent recommendation apparatus further includes:

the information acquisition module is used for acquiring user information and equipment information in the Internet of things platform;

the calibration module is used for calibrating the corresponding user tag with the user information;

the recommending module is used for determining recommending equipment information corresponding to the user tag based on the equipment information;

the establishing module is used for establishing the mapping relation between each user label and the corresponding recommendation equipment information to obtain a label mapping relation.

Optionally, the recommendation module includes:

a vector determining module for determining a first feature vector of the device information and a second feature vector of the user information;

the computing module is used for computing the feature distance of the first feature vector and the second feature vector;

and the recommended equipment information determining module is used for determining the equipment information with the characteristic distance smaller than a preset distance threshold value as recommended equipment information of the corresponding user tag.

Optionally, the transmission module includes:

the classification module is used for classifying the recommended equipment information based on the category labels of the preset equipment information to obtain recommended equipment information of a plurality of category sets;

The priority determining module is used for determining the transmission priority of the recommended equipment information of each category set;

the arrangement module is used for carrying out data arrangement on the recommendation equipment information of the class sets based on the transmission priority to obtain arranged recommendation equipment information;

and the batch transmission module is used for transmitting the arranged recommended equipment information batch to the user terminal based on a preset batch transmission rule.

the analysis module is used for analyzing the recommended equipment information into a target file in a preset format;

and the matrix determining module is used for determining the corresponding information matrix of the target file.

Optionally, the matrix determining module includes:

the partition module is used for partitioning the target file based on a preset information partition rule to obtain a block of the target file;

an information unit determining module, configured to determine an information unit in the block and coordinate information of the information unit;

the information matrix composition module is used for vectorizing the information units and the coordinate information of the information units, and composing the vectorized information units and the coordinate information of the information units into the information matrix corresponding to the target file.

the training data acquisition module is used for acquiring the equipment information set, the required information training data and the equipment information label of the required information training data;

and the training module is used for carrying out iterative training on a preset model to be trained based on the equipment information set, the demand information training data and the equipment information label of the demand information training data to obtain an equipment information recommendation model meeting the accuracy condition.

The specific implementation manner of the intelligent recommendation device for the equipment information is basically the same as that of each embodiment of the intelligent recommendation method for the equipment information, and is not repeated here.

Referring to fig. 1, fig. 1 is a schematic diagram of a terminal structure of a hardware running environment according to an embodiment of the present application.

Optionally, the device information intelligent recommendation device may further include a rectangular user interface, a network interface, a camera, an RF (Radio Frequency) circuit, a sensor, an audio circuit, a WiFi module, and the like. The rectangular user interface may include a Display screen (Display), an input sub-module such as a Keyboard (Keyboard), and the optional rectangular user interface may also include a standard wired interface, a wireless interface. The network interface may optionally include a standard wired interface, a wireless interface (e.g., WI-FI interface).

It will be appreciated by those skilled in the art that the device information intelligent recommendation device structure illustrated in FIG. 1 does not constitute a limitation of the device information intelligent recommendation device, and may include more or fewer components than illustrated, or may combine certain components, or may have a different arrangement of components.

As shown in fig. 1, an operating system, a network communication module, and a device information intelligent recommendation program may be included in the memory 1005 as one type of storage medium. The operating system is a program that manages and controls the device information intelligent recommendation device hardware and software resources, supporting the operation of the device information intelligent recommendation program and other software and/or programs. The network communication module is used for realizing communication among components in the memory 1005 and communication with other hardware and software in the device information intelligent recommendation system.

In the device information intelligent recommendation apparatus shown in fig. 1, a processor 1001 is configured to execute a device information intelligent recommendation program stored in a memory 1005, to implement the steps of the device information intelligent recommendation method described in any one of the above.

The specific implementation manner of the intelligent recommendation device for device information is basically the same as that of each embodiment of the intelligent recommendation method for device information, and is not repeated here.

The present application also provides a storage medium having stored thereon a program for implementing the device information intelligent recommendation method, the program for implementing the device information intelligent recommendation method being executed by a processor to implement the device information intelligent recommendation method as follows:

acquiring a user tag of a user of information to be recommended;

acquiring demand information of a user;

calibrating the user information to corresponding user labels;

and determining a corresponding information matrix of the target file.

The specific implementation manner of the storage medium is basically the same as that of each embodiment of the intelligent recommendation method for equipment information, and is not repeated here.

The application also provides a computer program product comprising a computer program which, when executed by a processor, implements the steps of the device information intelligent recommendation method described above.

The specific implementation manner of the computer program product of the present application is basically the same as the above embodiments of the device information intelligent recommendation method, and will not be described herein again.

It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.

The foregoing embodiment numbers of the present application are merely for describing, and do not represent advantages or disadvantages of the embodiments.

From the above description of the embodiments, it will be clear to those skilled in the art that the above-described embodiment method may be implemented by means of software plus a necessary general hardware platform, but of course may also be implemented by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a storage medium (such as ROM/RAM, magnetic disk, optical disk) as described above, including several instructions for causing a terminal device (which may be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to perform the method described in the embodiments of the present application.

The foregoing description is only of the preferred embodiments of the present application, and is not intended to limit the scope of the claims, and all equivalent structures or equivalent processes using the descriptions and drawings of the present application, or direct or indirect application in other related technical fields are included in the scope of the claims of the present application.

Claims

1. The intelligent recommending method for the equipment information is characterized by comprising the following steps of:

acquiring a user tag of a user of information to be recommended;

the determining the recommendation equipment information of the information user to be recommended based on the user label and a preset label mapping relation comprises the following steps:

calibrating the user information to corresponding user labels;

the determining recommended device information corresponding to the user tag based on the device information comprises the following steps:

determining the equipment information with the characteristic distance smaller than a preset distance threshold value as recommended equipment information of the corresponding user tag;

Establishing a mapping relation between each user tag and the corresponding recommendation equipment information to obtain a tag mapping relation;

acquiring demand information of a user; the requirement information is used for carrying out requirement retrieval on the recommendation equipment information of the information user to be recommended;

2. The intelligent recommendation method for device information according to claim 1, wherein the step of classifying the recommended device information and transmitting the classified recommended device information batch to the user terminal comprises:

3. The intelligent recommendation method for equipment information according to claim 1, wherein before the step of inputting the requirement information and the recommended equipment information into a preset equipment information recommendation model and performing requirement analysis processing on the requirement information and the recommended equipment information based on the equipment information recommendation model to obtain target equipment information, the method comprises:

and determining a corresponding information matrix of the target file.

4. The intelligent recommendation method for device information according to claim 3, wherein the step of determining the information matrix corresponding to the target file comprises:

5. The intelligent recommendation method for device information according to claim 1, wherein before the step of obtaining the requirement information of the user, the method comprises:

6. An intelligent recommendation device for equipment information, which is characterized by comprising:

the determining module is also used for acquiring user information and equipment information in the Internet of things platform; calibrating the user information to corresponding user labels; determining recommended equipment information corresponding to the user tag based on the equipment information; determining a first feature vector of the device information and a second feature vector of the user information; calculating the feature distance of the first feature vector and the second feature vector; determining the equipment information with the characteristic distance smaller than a preset distance threshold value as recommended equipment information of the corresponding user tag; establishing a mapping relation between each user tag and the corresponding recommendation equipment information to obtain a tag mapping relation;

the demand information acquisition module is used for acquiring demand information of a user; the requirement information is used for carrying out requirement retrieval on the recommendation equipment information of the information user to be recommended;

7. An intelligent recommendation device for device information, characterized in that the intelligent recommendation device for device information comprises: a memory, a processor and a program stored on the memory for implementing the device information intelligent recommendation method,

the processor is configured to execute a program for implementing the device information intelligent recommendation method to implement the steps of the device information intelligent recommendation method according to any one of claims 1 to 5.

8. A storage medium having stored thereon a program for realizing the device information intelligent recommendation method, the program for realizing the device information intelligent recommendation method being executed by a processor to realize the steps of the device information intelligent recommendation method according to any one of claims 1 to 5.