Projection method, device and electronic equipment for multi-person conference

Abstract

A projection method, device and electronic device for multi-person conferences, relating to the field of intelligent projection. In the method, multiple light intensity values ​​at different positions of the projection space are obtained; the multiple light intensity values ​​are weighted averaged to obtain the average light intensity value of the projection space; according to the average light intensity value, the projection brightness range corresponding to the average light intensity value is determined in a preset projection brightness library, and the preset projection brightness library includes the correspondence between the light intensity value and the projection brightness range; the vision parameters of each viewing user are obtained; the target projection brightness is determined within the projection brightness range according to the vision parameters; and the target projection image is generated according to the target projection brightness. The technical solution provided in the present application is implemented, the average light intensity of the conference room and the vision parameters of each user are comprehensively considered, the projection brightness is intelligently adjusted, and the visual experience of multi-person conferences is improved.

Description

Technical Field

[0001] The present application relates to the field of data processing, and in particular to a projection device and electronic equipment for multi-person conferences. Background Art

[0002] With the widespread use of multi-person conferences, more and more viewers are participating in the conference. In multi-person conferences, projection technology plays an important role, and the conference content is presented to multiple viewers through projection. However, different viewers have different vision and different requirements for projection brightness.

[0003] At present, most projection devices use a fixed projection brightness method. This method cannot fully consider the differences in vision and personalized needs of different viewers, resulting in users feeling that the brightness is not appropriate when watching, affecting the viewing experience.

[0004] Therefore, there is an urgent need for a projection method, device and electronic equipment for multi-person conferences. Summary of the invention

[0005] The present application provides a projection method, device and electronic device for multi-person conferences, which comprehensively consider the average light intensity of the conference room and the vision parameters of each user, intelligently adjust the projection brightness, and enhance the visual experience of multi-person conferences.

[0006] In a first aspect of the present application, a projection method for a multi-person conference is provided, the method comprising: obtaining multiple light intensity values ​​at different positions of a projection space; performing weighted averaging on the multiple light intensity values ​​to obtain an average light intensity value of the projection space; determining, based on the average light intensity value, a projection brightness range corresponding to the average light intensity value in a preset projection brightness library, wherein the preset projection brightness library includes a correspondence between light intensity values ​​and projection brightness ranges; obtaining vision parameters of each viewing user; determining a target projection brightness within the projection brightness range based on the vision parameters; and generating a target projection image based on the target projection brightness.

[0007] By adopting the above technical solution, multiple light intensity values ​​at different positions in the projection space are obtained, and the average light intensity value is obtained by weighted averaging. The corresponding projection brightness range is determined in the preset projection brightness library according to the average value. At the same time, the vision parameters of each viewing user are obtained, and the optimal target projection brightness is determined within the projection brightness range according to the vision parameters, and the final target projection image is generated based on the target projection brightness. In this way, by comprehensively considering the actual lighting conditions of the projection environment and the vision conditions of the viewing users, a balanced projection brightness is adaptively determined, which can adapt to lighting changes and take into account the viewing needs of users with different vision, so that the generated projection image brightness is optimal, improving the viewing experience.

[0008] Optionally, determining the target projection brightness within the projection brightness range according to the vision parameters specifically includes: performing cluster analysis on the multiple viewing users according to the vision parameters to obtain multiple viewing user combinations; obtaining the number of viewing users in each viewing user combination; sorting each of the user numbers from most to least to obtain a target number of users and a target viewing user combination corresponding to the target number of users, the target number of users being the largest number of users among the multiple user numbers; and determining the target projection brightness corresponding to the target viewing user combination within the projection brightness range.

[0009] By adopting the above technical solution, cluster analysis is performed on viewing users according to vision parameters to obtain multiple viewing user combinations, and then the number of users in each viewing user combination is obtained and sorted from most to least, and the target viewing user combination with the largest number of users and its corresponding vision parameters are used as the main reference for determining the projection brightness. Users with similar vision are first grouped together through clustering, and then the group with the largest number of users is given priority, which is equivalent to taking the visual needs of the majority of people as the standard, making the determination of projection brightness more universal and fair, taking into account the viewing experience of the majority of people as much as possible, and having a certain group optimal effect.

[0010] Optionally, cluster analysis is performed on the multiple viewing users according to the vision parameters to obtain multiple viewing user combinations, specifically including: the vision parameters are grouped into a data set, the data set includes multiple data points, one of the data points represents one vision parameter; determining a preset number of target categories, and determining initial centers from the data set, the number of the initial centers is the preset number of target categories, and one initial center corresponds to one clustering category; calculating the Euclidean distance between the data point and each initial center; sorting the Euclidean distances from small to large; if it is determined that the target Euclidean distance between the target data point and the target initial center is the smallest, then assigning the target data point to the target clustering category where the target initial center is located, the target data point is any one of the multiple data points, and the target initial center is any one of the initial centers; updating the initial center to obtain multiple viewing user combinations.

[0011] By adopting the above technical solution, by calculating the Euclidean distance between the vision parameter and the initial center, users with similar vision parameters are divided into the same category, and the cluster center is continuously optimized iteratively, and finally a combination of multiple users with similar vision levels is obtained. This clustering method can quickly and accurately group users according to their vision characteristics.

[0012] Optionally, the updating of the initial center to obtain the multiple viewing user combinations specifically includes: calculating the average vision parameter of the data points contained in each of the clustering categories, and iterating the average vision parameter as the new center to obtain the number of iterations; judging whether the number of iterations is greater than or equal to the preset number of iterations; if it is determined that the number of iterations is greater than or equal to the preset number of iterations, stopping the iteration to obtain the multiple viewing user combinations.

[0013] By adopting the above technical solution, the average vision parameter of each cluster category is calculated as the new center, and it is iterated until the preset number of iterations is reached. This process continuously reduces the difference in vision within the group and increases the difference between groups, so that the vision level of the user combination obtained in the end tends to be consistent, and the difference between groups is obvious, which is more conducive to the subsequent selection of the best projection brightness.

[0014] Optionally, determining the target projection brightness corresponding to the target viewing user group within the projection brightness range specifically includes: obtaining target vision parameters of the target viewing users included in the target viewing user group; calculating the average value of the target vision parameters to obtain a target average vision parameter; and inputting the projection brightness range and the target average vision parameter into a preset brightness model to obtain the target projection brightness.

[0015] By adopting the above technical solution, after determining the target viewing user combination, the preset brightness model is further used to calculate the optimal target projection brightness within the projection brightness range according to the average vision parameters of the target viewing user combination. The introduction of the preset brightness model can more accurately and quantitatively predict the optimal projection brightness, and improve the intelligent level of projection brightness selection.

[0016] Optionally, the preset brightness model includes an input layer, a hidden layer, and an output layer. Before obtaining multiple light intensity values ​​at different positions in the projection space, the method also includes: obtaining historical vision parameters and historical projection brightness; using the historical vision parameters as input of the input layer, and using the historical projection brightness as output of the output layer; and learning the nonlinear relationship between the historical vision parameters and the historical projection brightness through multiple hidden layers to obtain the preset brightness model.

[0017] By adopting the above technical solution, a neural network model including input layer, hidden layer and output layer is constructed, with historical vision parameters as input and historical projection brightness as output, and the nonlinear mapping relationship between the two is trained and learned, thus obtaining a mature preset brightness model. Once the model training is completed, the optimal projection brightness can be quickly predicted based on the newly input vision parameters.

[0018] Optionally, the step of inputting the projection brightness range and the target average vision parameter into a preset brightness model to obtain the target projection brightness specifically includes: inputting the target average vision parameter into the preset brightness model to obtain an initial projection brightness; determining whether the initial projection brightness is within the projection brightness range; if it is determined that the initial projection brightness is within the projection brightness range, outputting the initial projection brightness as the target projection brightness; if it is determined that the initial projection brightness is less than a lower limit of the projection brightness range, outputting the lower limit as the target projection brightness; if it is determined that the initial projection brightness is greater than an upper limit of the projection brightness range, outputting the upper limit as the target projection brightness.

[0019] By adopting the above technical solution, after obtaining the initial projection brightness using the preset brightness model, it is further determined whether it falls within the projection brightness range. If it exceeds the projection brightness range, the upper and lower limits of the range are taken as the final target projection brightness. This correction process ensures that no matter what the predicted value of the preset brightness model is, the final output target projection brightness is within an acceptable and reasonable range, avoiding overbrightness or overdarkness that affects the projection effect and user experience.

[0020] In a second aspect of the present application, a projection device for a multi-person conference is provided, the device comprising: an acquisition module and a processing module, wherein: the acquisition module is used to acquire multiple light intensity values ​​at different positions of a projection space; the processing module is used to perform weighted averaging on the multiple light intensity values ​​to obtain an average light intensity value of the projection space; the processing module is also used to determine, based on the average light intensity value, a projection brightness range corresponding to the average light intensity value in a preset projection brightness library, wherein the preset projection brightness library includes a correspondence between light intensity values ​​and projection brightness ranges; the acquisition module is also used to acquire vision parameters of each viewing user; the processing module is also used to determine a target projection brightness within the projection brightness range based on the vision parameters; the processing module is also used to generate a target projection image based on the target projection brightness.

[0021] In the third aspect of the present application, an electronic device is provided, including a processor, a memory, a user interface and a network interface, the memory is used to store instructions, the user interface and the network interface are both used to communicate with other devices, and the processor is used to execute the instructions stored in the memory so that the electronic device executes any one of the methods described above.

[0022] In a fourth aspect of the present application, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores instructions, and when the instructions are executed, any of the methods described above is executed.

[0023] In summary, one or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:

[0024] 1. Obtain multiple light intensity values ​​at different positions in the projection space, perform weighted averaging to obtain an average light intensity value, and determine the corresponding projection brightness range in the preset projection brightness library based on the average value. At the same time, obtain the vision parameters of each viewing user, determine the optimal target projection brightness within the projection brightness range based on the vision parameters, and generate the final target projection image based on the target projection brightness. In this way, by comprehensively considering the actual lighting conditions of the projection environment and the vision of the viewing user, a balanced projection brightness is adaptively determined, which can adapt to lighting changes and take into account the viewing needs of users with different vision, so that the generated projection image has the best brightness and improves the viewing experience.

[0025] 2. Perform cluster analysis on viewing users according to vision parameters to obtain multiple viewing user combinations, then obtain the number of users in each viewing user combination and sort them from most to least, and use the target viewing user combination with the largest number of users and its corresponding vision parameters as the main reference for determining the projection brightness. Through clustering, users with similar vision are first grouped together, and then the group with the largest number of users is given priority, which is equivalent to taking the visual needs of the majority of people as the standard, making the determination of projection brightness more universal and fair, taking into account the viewing experience of the majority of people as much as possible, and having a certain group optimal effect.

[0026] 3. By calculating the Euclidean distance between the vision parameter and the initial center, users with similar vision parameters are divided into the same category, and the cluster center is continuously optimized iteratively to finally obtain multiple user combinations with similar vision levels. This clustering method can quickly and accurately group users according to their vision characteristics. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 It is a flowchart of a projection method for a multi-person conference disclosed in an embodiment of the present application;

[0028] Figure 2 It is a module schematic diagram of a projection device for multi-person conference disclosed in an embodiment of the present application;

[0029] Figure 3 It is a structural schematic diagram of an electronic device disclosed in an embodiment of the present application.

[0030] Explanation of the reference numerals: 201, acquisition module; 202, processing module; 300, electronic device; 301, processor; 302, communication bus; 303, user interface; 304, network interface; 305, memory. DETAILED DESCRIPTION

[0031] In order to enable technicians in this field to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this application, not all of the embodiments.

[0032] In the description of the embodiments of the present application, words such as "for example" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "for example" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "for example" or "for example" is intended to present related concepts in a specific way.

[0033] In the description of the embodiments of the present application, the meaning of the term "multiple" refers to two or more. For example, multiple systems refer to two or more systems, and multiple screen terminals refer to two or more screen terminals. In addition, the terms "first" and "second" are used for descriptive purposes only and cannot be understood as indicating or implying relative importance or implicitly indicating the indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. The terms "include", "comprise", "have" and their variations all mean "including but not limited to", unless otherwise specifically emphasized.

[0034] This application provides a projection method for multi-person conferences, referring to Figure 1 , Figure 1 1 is a flowchart of a projection method for a multi-person conference provided in an embodiment of the present application. The method is applied to a server and includes steps S101 to S106, which are as follows:

[0035] Step S101: Acquire multiple illumination intensity values ​​at different positions in the projection space.

[0036] In step S101, the server obtains the light intensity value of the projection space by connecting to the light intensity sensor. The server sends a light intensity collection instruction to the light intensity sensor. After the light intensity sensor starts working, it will sample the light intensity at different positions in the projection space. The light intensity sensor can use a partition sampling method to divide the projection space into several sub-areas, and select one or more sampling points in each sub-area. For example, the projection space can be divided into 9 sub-areas according to a 3x3 grid, and the light intensity is sampled at the center of each sub-area. During the sampling process, the light intensity sensor will report the collected light intensity value and the corresponding position coordinate information to the server in real time.

[0037] Step S102: performing weighted averaging on the plurality of illumination intensity values ​​to obtain an average illumination intensity value of the projection space.

[0038] In step S102, the server performs weighted averaging on the multiple illumination intensity values ​​obtained in step S101 to calculate the average illumination intensity value of the projection space. The purpose of weighted averaging is to consider the importance differences of illumination intensity at different locations and to make a more accurate assessment of the overall illumination environment. The server reads the multiple illumination intensity values ​​of step S101. For each illumination intensity value, the server determines a weight coefficient according to its position coordinates, and the corresponding relationship between the position coordinates and the weight coefficient is stored in a preset weight database. The value of the weight coefficient can be pre-set by the user according to the importance of the position, and this application does not limit this. For example, the illumination intensity in the central area of ​​the projection space may have a greater impact on the viewing experience, so a higher weight coefficient can be assigned; while the illumination intensity in the edge area has a relatively small impact, and a lower weight coefficient can be assigned. After determining the weight coefficient, the server performs weighted summation on the illumination intensity values. Specifically, the server multiplies each illumination intensity value by its corresponding weight coefficient, and then adds all the products. Finally, the result of the weighted summation is divided by the sum of the weight coefficients to obtain a weighted average illumination intensity value, which is the average illumination intensity value of the projection space.

[0039] Step S103: according to the average illumination intensity value, determining a projection brightness range corresponding to the average illumination intensity value in a preset projection brightness library, wherein the preset projection brightness library includes a correspondence between illumination intensity values ​​and projection brightness ranges.

[0040] In step S103, the server determines the projection brightness range corresponding to the average light intensity value in the preset projection brightness library according to the calculated average light intensity value. The preset projection brightness library is a pre-constructed data set, which contains the mapping relationship between different light intensity values ​​and corresponding projection brightness ranges. The construction of the preset projection brightness library comprehensively considers many factors, such as the performance parameters of the projection equipment, the ambient light conditions, and the visual characteristics of the human eye. Through a large number of experimental tests and data analysis in advance, it can be summarized that the optimal brightness range that the projection equipment should adopt under different light intensities. After determining the projection brightness range, the server uses the projection brightness range as a reference for subsequent projection brightness adjustments.

[0041] Step S104: Obtain vision parameters of each viewing user.

[0042] In step S104, the server needs to obtain the vision parameters of each user who views the projection content. The vision parameters include vision and diopter. Among them, vision includes naked eye vision and corrected vision, and diopter includes spherical power and cylindrical power. Vision is a measure of the ability of the human eye to recognize the details of an object. The lower the vision, the viewer may need a higher projection brightness to clearly see the projection content. Conversely, the higher the vision, the viewer may have relatively lower requirements for projection brightness. Diopter reflects the refractive state of the eyeball and is closely related to the user's vision. Spherical power indicates the degree of myopia or hyperopia, and cylindrical power indicates the degree of astigmatism. The higher the degree of myopia or astigmatism, the user needs a higher projection brightness to compensate for the lack of vision.

[0043] Vision parameters can be obtained in the following ways: The server can ask users to provide their vision information when registering or booking a meeting. Users can manually enter or select their own vision parameters. The server can be connected to special intelligent vision testing equipment, such as automatic computer ophthalmometers and comprehensive ophthalmometers. Users can use these devices to perform fast and accurate vision tests before using the multi-person conference system. The testing equipment automatically uploads the measurement results to the server, which associates and stores them with the user account.

[0044] After the server obtains each user's vision parameters, it will associate them with the user's identity information and store them in the database.

[0045] Step S105: determining a target projection brightness within the projection brightness range according to the vision parameter.

[0046] In step S105, cluster analysis is performed on the multiple viewing users according to the vision parameters to obtain multiple viewing user combinations; the number of viewing users in each viewing user combination is obtained; each of the user numbers is sorted from most to least to obtain a target number of users and a target viewing user combination corresponding to the target number of users, wherein the target number of users is the largest number of users among the multiple user numbers; and the target projection brightness corresponding to the target viewing user combination is determined within the projection brightness range.

[0047] Specifically, the server performs cluster analysis on multiple viewing users according to vision parameters. In the present application, the server groups users with similar vision parameters into a group to form multiple viewing user combinations. After the cluster analysis is completed, the server will obtain multiple viewing user combinations, each of which contains a part of users with similar vision parameters. Next, the server will count the number of users in each viewing user combination, that is, calculate how many viewing users are contained in each viewing user combination. After obtaining the number of users in each viewing user combination, the server will sort these user numbers in order from most to least, and then determine the viewing user combination with the largest number of users, that is, the target viewing user combination. The target viewing user combination represents the user group with the largest proportion in the current viewing scene, and meeting their viewing needs is the most critical to improving the overall viewing experience. After determining the target viewing user combination, the server will select a target projection brightness suitable for the vision characteristics of the target viewing user combination within the previously determined projection brightness range.

[0048] In a possible implementation, cluster analysis is performed on the plurality of viewing users according to the vision parameters to obtain a plurality of viewing user combinations, specifically comprising: forming the vision parameters into a data set, the data set including a plurality of data points, wherein one of the data points represents one vision parameter; determining a preset number of target categories, and determining initial centers from the data set, the number of the initial centers being the preset number of target categories, and one initial center corresponding to one clustering category; calculating the Euclidean distance between the data point and each of the initial centers; sorting the Euclidean distances from small to large; if it is determined that the target Euclidean distance between the target data point and the target initial center is the smallest, assigning the target data point to the target clustering category where the target initial center is located, the target data point being any one of the plurality of data points, and the target initial center being any one of the initial centers; updating the initial center to obtain a plurality of viewing user combinations.

[0049] Specifically, the server collects the vision parameters of multiple viewing users to form a data set. Each data point in the data set represents the vision parameters of a user, including four dimensions: naked eye vision, corrected vision, spherical degree and cylindrical degree. This data set can be regarded as a point set in a multidimensional space, in which each data point corresponds to the vision parameters of a user. For example, if there are 100 viewing users, and the vision parameter of each user is a real number, then this data set can be regarded as 100 points in a 100-dimensional space. The server determines the number of preset target categories for clustering, that is, it is ultimately hoped that the viewing users will be divided into several combinations. The number of preset target categories can be set according to actual needs, and this application does not limit this. After determining the number of preset target categories, the server needs to select the initial center from the data set. The initial center is the "representative point" of each clustering category, and the subsequent clustering process is to continuously assign data points to the clustering category where the nearest initial center is located. The selection of the initial center can be carried out by random sampling, that is, randomly selecting points of the preset target category number from the data set as the initial center. After the initialization is completed, the server starts the iterative clustering process. In each iteration, the server first calculates the Euclidean distance between each data point and each initial center.

[0050] The server calculates the distance between each data point and all the initial centers to obtain multiple Euclidean distances. The server sorts the multiple Euclidean distances from small to large and finds the initial center with the smallest Euclidean distance. This means that the current data point is closest to the initial center and should be assigned to the category where the initial center is located. The server traverses all data points and assigns each data point to the category corresponding to the nearest initial center. After completing a round of data point allocation, the server needs to update the initial center to obtain a new center. The new center is the "center" of all data points in each cluster category, represented by their mean. The server calculates the mean of the data points in each cluster category to obtain the new center coordinates. After updating the initial center, the server determines whether the iteration termination condition is met. In an embodiment of the present application, the termination condition is to reach a preset number of iterations.

[0051] In a possible implementation, the initial center is updated to obtain a plurality of viewing user combinations, specifically including: calculating an average vision parameter of the data points included in each of the clustering categories, and iterating using the average vision parameter as the new center to obtain an iteration number; determining whether the iteration number is greater than or equal to a preset iteration number; if it is determined that the iteration number is greater than or equal to the preset iteration number, stopping the iteration to obtain a plurality of viewing user combinations.

[0052] Specifically, at the beginning of each iteration, the server calculates the average vision parameter of the data points contained in each cluster category, that is, for the i-th cluster category, find all the data points belonging to the cluster category, extract their vision parameters, and calculate the arithmetic mean. The average vision parameter represents the overall vision level of the category and can be used as the new center.

[0053] The server uses the calculated average vision parameter as the new center and starts a new round of iteration. Specifically, the server uses the new center to recalculate the Euclidean distance between each data point and each new center, and assigns each data point to the cluster category where the new center with the closest Euclidean distance is located. This step is similar to the previous data point assignment process, except that the updated new center is used.

[0054] In this way, the server completes an update of the new center and a redistribution of the data points. This process will change the data points contained in each clustering category, thereby affecting the average vision parameter calculated in the next round of iteration. The new average vision parameter will continue to be iterated as the new center to continuously optimize the clustering results. After each round of iteration, the server will add 1 to the current number of iterations and determine whether the number of iterations has reached the preset number of iterations. The preset number of iterations indicates the maximum number of iterations that the algorithm needs to perform, which can be set based on experience or experiments, and this application does not limit this.

[0055] For example, suppose the preset number of iterations is 10. After executing the first round of iterations, the server updates the number of iterations to 1 and determines whether 1 is greater than or equal to 10. Since 1 is less than 10, the server continues to execute the next round of iterations. After the second round of iterations, the number of iterations becomes 2, which is still less than 10, so the iteration continues. And so on, the server continuously updates the center, redistributes data points, and updates the number of iterations until the 10th round of iterations is completed.

[0056] When the number of iterations reaches the preset number of iterations, the server stops the iteration process and uses the current clustering result as the final viewing user combination. At this time, each clustering category corresponds to a viewing user combination, which includes a group of users with similar vision parameters.

[0057] In a possible implementation, the target projection brightness corresponding to the target viewing user group is determined within the projection brightness range, specifically including: obtaining target vision parameters of the target viewing users included in the target viewing user group; calculating the average value of the target vision parameters to obtain a target average vision parameter; and inputting the projection brightness range and the target average vision parameter into a preset brightness model to obtain the target projection brightness.

[0058] Among them, the projection brightness range and the target average vision parameter are input into a preset brightness model to obtain the target projection brightness, specifically including: inputting the target average vision parameter into the preset brightness model to obtain an initial projection brightness; judging whether the initial projection brightness is within the projection brightness range; if it is determined that the initial projection brightness is within the projection brightness range, outputting the initial projection brightness as the target projection brightness; if it is determined that the initial projection brightness is less than the lower limit of the projection brightness range, outputting the lower limit as the target projection brightness; if it is determined that the initial projection brightness is greater than the upper limit of the projection brightness range, outputting the upper limit as the target projection brightness.

[0059] Specifically, the server extracts the vision parameters of all target viewing users in the target viewing user combination according to the target viewing user combination determined in step S105, including naked eye vision, corrected vision, spherical degree and cylindrical degree. The server averages the vision parameters of all target viewing users in the target viewing user combination to obtain a target average vision parameter. Specifically, the server calculates the average values ​​of the four dimensions of naked eye vision, corrected vision, spherical degree and cylindrical degree respectively to obtain a four-dimensional target average vision parameter vector. For example, assuming that there are three target viewing users in the target viewing user combination, their vision parameters are as follows: User 1, naked eye vision 0.5, corrected vision 1.0, spherical degree -2.50, cylindrical degree -0.50; User 2, naked eye vision 0.6, corrected vision 1.0, spherical degree -2.00, cylindrical degree -0.75; User 3, naked eye vision 0.4, corrected vision 0.9, spherical degree -3.00, cylindrical degree -0.25. The server calculates the average value and obtains the target average vision parameter vector: the average naked eye vision is (0.5+0.6+0.4) / 3=0.5, the average corrected vision is (1.0+1.0+0.9) / 3=0.97, the average spherical power is (-2.50+-2.00+-3.00) / 3=-2.50, and the average cylindrical power is (-0.50+-0.75+-0.25) / 3=-0.50. Therefore, the target average vision parameters are (0.5, 0.97, -2.50, -0.50).

[0060] The server inputs the target average vision parameter vector into a preset brightness model, and the preset brightness model outputs an initial projection brightness. The server compares the initial projection brightness with the size of the projection brightness range obtained in step S103 to determine whether it is within the projection brightness range, and the projection brightness range is a closed interval. If the initial projection brightness is within this range, the server outputs it as the final target projection brightness. If the initial projection brightness is less than the lower limit of the projection brightness range, the server outputs the lower limit as the target projection brightness. If the initial projection brightness is greater than the upper limit of the projection brightness range, the server outputs the upper limit (800 nits) as the target projection brightness.

[0061] In a possible implementation, the construction process of the preset brightness model includes: the preset brightness model includes an input layer, a hidden layer and an output layer, and historical vision parameters and historical projection brightness are obtained; the historical vision parameters are used as input of the input layer, and the historical projection brightness is used as output of the output layer; through multiple hidden layers, the nonlinear relationship between the historical vision parameters and the historical projection brightness is learned to obtain the preset brightness model.

[0062] Specifically, the server first determines the structure of the preset brightness model, and adopts a multi-layer feedforward neural network including an input layer, a hidden layer and an output layer. The number of neurons in the input layer is the same as the dimension of the vision parameter. For example, if the vision parameter includes four indicators of naked eye vision, corrected vision, spherical power and cylindrical power, the input layer includes four neurons, which receive the values ​​of these four parameters respectively. The output layer only includes one neuron, which is used to output the predicted projection brightness value. The number of hidden layers and the number of neurons in each layer can be designed according to actual needs, and this application is not limited to this. In an embodiment of the present application, the server designs a neural network including two hidden layers, the first hidden layer includes 8 neurons, and the second hidden layer includes 4 neurons. Each hidden layer uses a ReLU activation function, and the output layer uses a linear activation function. After determining the preset brightness model structure, the server needs to prepare training data. The training data includes two parts: historical vision parameters and corresponding historical projection brightness. The server queries the user vision parameters and the historical projection brightness of the projection device within a certain time range from the database, and combines them into training samples. Each training sample includes a set of vision parameters (such as naked eye vision, corrected vision, spherical power and cylindrical power) and corresponding projection brightness values. After data preparation is completed, the server starts training the preset brightness model. The historical vision parameters are used as the input of the input layer, and the historical projection brightness is used as the expected output of the output layer. The model is trained using supervised learning. During the training process, the server continuously calculates the mean square error between the predicted projection brightness and the actual projection brightness until the mean square error is less than the preset error. The server stops training and obtains the preset brightness model.

[0063] Step S106: generating a target projection image according to the target projection brightness.

[0064] In step S106, the server obtains the original projection image from the content provider or local storage, and the original projection image is created under standard brightness conditions. The server calculates a brightness adjustment coefficient based on the target projection brightness and the standard brightness. The brightness adjustment coefficient represents the scaling ratio required to adjust the brightness of the original projection image to the target projection brightness. The server traverses each pixel block of the original projection image, multiplies the brightness value of the pixel by the brightness adjustment coefficient, and obtains the adjusted brightness value. The server applies the adjusted brightness value to each pixel of the original image to generate a target projection image with adjusted brightness. The server outputs the generated target projection image to the projection device, which projects it onto a screen or other projection surface.

[0065] Reference Figure 2 The present application also provides a projection device for a multi-person conference, which is a server, and the server includes an acquisition module 201 and a processing module 202, wherein the acquisition module 201 is used to acquire multiple light intensity values ​​at different positions of the projection space; the processing module 202 is used to perform weighted averaging on the multiple light intensity values ​​to obtain an average light intensity value of the projection space; the processing module 202 is also used to determine, according to the average light intensity value, a projection brightness range corresponding to the average light intensity value in a preset projection brightness library, wherein the preset projection brightness library includes a correspondence between light intensity values ​​and projection brightness ranges; the acquisition module 201 is also used to acquire vision parameters of each viewing user; the processing module 202 is also used to determine a target projection brightness within the projection brightness range according to the vision parameters; the processing module 202 is also used to generate a target projection image according to the target projection brightness.

[0066] In a possible implementation, the processing module 202 determines the target projection brightness within the projection brightness range according to the vision parameters, specifically including: the processing module 202 performs cluster analysis on the multiple viewing users according to the vision parameters to obtain multiple viewing user combinations; the acquisition module 201 obtains the number of viewing users in each viewing user combination; the processing module 202 sorts each of the user numbers from most to least to obtain the target number of users and the target viewing user combination corresponding to the target number of users, the target number of users being the largest number of users among the multiple user numbers; the processing module 202 determines the target projection brightness corresponding to the target viewing user combination within the projection brightness range.

[0067] In a possible implementation, the processing module 202 performs cluster analysis on the plurality of viewing users according to the vision parameters to obtain a plurality of viewing user combinations, specifically including: the processing module 202 organizes the vision parameters into a data set, the data set includes a plurality of data points, one of the data points represents one vision parameter; the processing module 202 determines the preset number of target categories, and determines the initial centers from the data set, the number of the initial centers is the preset number of target categories, and one initial center corresponds to one clustering category; the processing module 202 calculates the Euclidean distance between the data point and each of the initial centers; the processing module 202 sorts each of the Euclidean distances from small to large; if the processing module 202 determines that the target Euclidean distance between the target data point and the target initial center is the smallest, the target data point is assigned to the target clustering category where the target initial center is located, the target data point is any one of the plurality of data points, and the target initial center is any one of the initial centers; the processing module 202 updates the initial center to obtain a plurality of viewing user combinations.

[0068] In a possible implementation, the processing module 202 updates the initial center to obtain a plurality of viewing user combinations, specifically including: the processing module 202 calculates the average vision parameter of the data points included in each of the clustering categories, and iterates the average vision parameter as the new center to obtain the number of iterations; the processing module 202 determines whether the number of iterations is greater than or equal to the preset number of iterations; if the processing module 202 determines that the number of iterations is greater than or equal to the preset number of iterations, the iteration is stopped to obtain a plurality of viewing user combinations.

[0069] In a possible implementation, the processing module 202 determines the target projection brightness corresponding to the target viewing user group within the projection brightness range, specifically including: the acquisition module 201 acquires the target vision parameters of the target viewing users included in the target viewing user group; the processing module 202 calculates the average value of the target vision parameters to obtain the target average vision parameters; the processing module 202 inputs the projection brightness range and the target average vision parameters into a preset brightness model to obtain the target projection brightness.

[0070] In a possible implementation, the preset brightness model includes an input layer, a hidden layer, and an output layer. Before the acquisition module 201 acquires multiple light intensity values ​​at different positions in the projection space, the method also includes: the acquisition module 201 acquires historical vision parameters and historical projection brightness; the processing module 202 uses the historical vision parameters as input of the input layer, and uses the historical projection brightness as output of the output layer; the processing module 202 learns the nonlinear relationship between the historical vision parameters and the historical projection brightness through multiple hidden layers to obtain the preset brightness model.

[0071] In a possible implementation, the processing module 202 inputs the projection brightness range and the target average vision parameter into a preset brightness model to obtain the target projection brightness, specifically including: the processing module 202 inputs the target average vision parameter into the preset brightness model to obtain an initial projection brightness; the processing module 202 determines whether the initial projection brightness is within the projection brightness range; if the processing module 202 determines that the initial projection brightness is within the projection brightness range, the initial projection brightness is output as the target projection brightness; if the processing module 202 determines that the initial projection brightness is less than the lower limit of the projection brightness range, the lower limit is output as the target projection brightness; if the processing module 202 determines that the initial projection brightness is greater than the upper limit of the projection brightness range, the upper limit is output as the target projection brightness.

[0072] It should be noted that: when the device provided in the above embodiment realizes its function, only the division of the above functional modules is used as an example. In actual application, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the device and method embodiments provided in the above embodiment belong to the same concept, and the specific implementation process is detailed in the method embodiment, which will not be repeated here.

[0073] The present application also provides an electronic device. Figure 3 , Figure 3 The electronic device 300 may include: at least one processor 301 , at least one network interface 304 , a user interface 303 , a memory 305 , and at least one communication bus 302 .

[0074] The communication bus 302 is used to realize the connection and communication between these components.

[0075] The user interface 303 may include a display screen (Display) and a camera (Camera). Optionally, the user interface 303 may also include a standard wired interface and a wireless interface.

[0076] The network interface 304 may optionally include a standard wired interface or a wireless interface (such as a WI-FI interface).

[0077] Among them, the processor 301 may include one or more processing cores. The processor 301 uses various interfaces and lines to connect various parts in the entire server, and executes various functions of the server and processes data by running or executing instructions, programs, code sets or instruction sets stored in the memory 305, and calling data stored in the memory 305. Optionally, the processor 301 can be implemented in at least one hardware form of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), and programmable logic array (Programmable Logic Array, PLA). The processor 301 can integrate one or a combination of a central processing unit (Central Processing Unit, CPU), a graphics processing unit (Graphics Processing Unit, GPU) and a modem. Among them, the CPU mainly processes the operating system, user interface and application programs; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 301, and it can be implemented separately through a chip.

[0078] Among them, the memory 305 may include a random access memory (Random Access Memory, RAM) and may also include a read-only memory (Read-Only Memory). Optionally, the memory 305 includes a non-transitory computer-readable storage medium. The memory 305 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 305 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store data involved in the above-mentioned various method embodiments, etc. The memory 305 may optionally also be at least one storage device located away from the aforementioned processor 301. Refer to Figure 3, the memory 305 as a computer storage medium may include an operating system, a network communication module, a user interface module and an application program for a projection method for a multi-person conference.

[0079] exist Figure 3 In the electronic device 300 shown, the user interface 303 is mainly used to provide an input interface for the user and obtain the data input by the user; and the processor 301 can be used to call the application program stored in the memory 305 for a projection method for a multi-person conference, and when executed by one or more processors 301, the electronic device 300 executes one or more of the methods described in the above embodiments. It should be noted that for the aforementioned method embodiments, for the sake of simple description, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required for the present application.

[0080] The present application also provides a computer-readable storage medium, which stores instructions. When executed by one or more processors 301, the electronic device 300 executes one or more of the methods described in the above embodiments.

[0081] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0082] In the several embodiments provided in this application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some service interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0083] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0084] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0085] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a memory and includes several instructions for a computer device (which can be a personal computer, server or network device, etc.) to execute all or part of the steps of the various embodiments of the present application. The aforementioned memory includes: various media that can store program codes, such as USB flash drives, mobile hard drives, magnetic disks or optical disks.

[0086] The above is only an exemplary embodiment of the present disclosure and cannot be used to limit the scope of the present disclosure. That is, any equivalent changes and modifications made according to the teachings of the present disclosure are still within the scope of the present disclosure. After considering the disclosure of the specification and the truth of practice, those skilled in the art will easily think of other embodiments of the present disclosure.

[0087] This application is intended to cover any variation, use or adaptation of the present disclosure, which follows the general principles of the present disclosure and includes common knowledge or customary technical means in the art not described in the present disclosure. The description and examples are to be regarded as exemplary only, and the scope and spirit of the present disclosure are defined by the claims.

Claims

1. A projection method for a multi-person conference, characterized in that: The method comprises: Get multiple light intensity values ​​at different positions in the projection space; Taking a weighted average of the plurality of illumination intensity values ​​to obtain an average illumination intensity value of the projection space; According to the average illumination intensity value, determining a projection brightness range corresponding to the average illumination intensity value in a preset projection brightness library, wherein the preset projection brightness library includes a correspondence between illumination intensity values ​​and projection brightness ranges; Obtain vision parameters of each viewing user; Determining a target projection brightness within the projection brightness range according to the vision parameter; Generate a target projection image according to the target projection brightness; Determining the target projection brightness within the projection brightness range according to the vision parameter specifically includes: performing cluster analysis on the plurality of viewing users according to the vision parameter to obtain a plurality of viewing user combinations; Obtaining the number of users who watch the user in each of the viewing user groups; Sort the numbers of users from most to least to obtain a target number of users and a target viewing user combination corresponding to the target number of users, wherein the target number of users is the largest number of users among the multiple numbers of users; Determining a target projection brightness corresponding to the target viewing user combination within the projection brightness range; The cluster analysis is performed on the plurality of viewing users according to the vision parameter to obtain a plurality of viewing user combinations, specifically including: Combining the vision parameters into a data set, wherein the data set includes a plurality of data points, wherein one of the data points represents one of the vision parameters; Determine a preset number of target categories, and determine initial centers from the data set, the number of the initial centers being the preset number of target categories, and one initial center corresponding to one clustering category; Calculate the Euclidean distance between the data point and each of the initial centers; Sort the Euclidean distances from small to large; If it is determined that the target Euclidean distance between the target data point and the target initial center is the smallest, the target data point is assigned to the target cluster category where the target initial center is located, the target data point is any one of the multiple data points, and the target initial center is any one of the initial centers; Updating the initial center to obtain a plurality of viewing user combinations; The updating of the initial center to obtain a plurality of viewing user combinations specifically includes: Calculating the average vision parameter of the data points included in each of the cluster categories, and taking the average vision parameter as a new center for iteration to obtain the number of iterations; Determine whether the number of iterations is greater than or equal to a preset number of iterations; If it is determined that the number of iterations is greater than or equal to the preset number of iterations, the iteration is stopped to obtain a plurality of viewing user combinations.

2. The method according to claim 1, characterized in that Determining the target projection brightness corresponding to the target viewing user group within the projection brightness range specifically includes: Acquire target vision parameters of target viewing users included in the target viewing user group; Calculating the average value of the target vision parameter to obtain the target average vision parameter; The projection brightness range and the target average vision parameter are input into a preset brightness model to obtain the target projection brightness.

3. The method according to claim 2, characterized in that The preset brightness model includes an input layer, a hidden layer, and an output layer. Before acquiring a plurality of illumination intensity values ​​at different positions of the projection space, the method further includes: Get historical vision parameters and historical projection brightness; Using the historical vision parameter as input of the input layer, and using the historical projection brightness as output of the output layer; The nonlinear relationship between the historical vision parameters and the historical projection brightness is learned through the multiple hidden layers to obtain the preset brightness model.

4. The method according to claim 2, characterized in that: The step of inputting the projection brightness range and the target average vision parameter into a preset brightness model to obtain the target projection brightness specifically includes: Inputting the target average vision parameter into the preset brightness model to obtain an initial projection brightness; Determining whether the initial projection brightness is within the projection brightness range; If it is determined that the initial projection brightness is within the projection brightness range, outputting the initial projection brightness as the target projection brightness; If it is determined that the initial projection brightness is less than the lower limit of the projection brightness range, the lower limit is output as the target projection brightness; If it is determined that the initial projection brightness is greater than the upper limit of the projection brightness range, the upper limit is output as the target projection brightness.

5. A projection device for multi-person conference, characterized in that: The device is used to execute the method according to any one of claims 1 to 4, and comprises an acquisition module (201) and a processing module (202), wherein: The acquisition module (201) is used to acquire multiple illumination intensity values ​​at different positions in the projection space; The processing module (202) is used to perform weighted averaging on the plurality of illumination intensity values ​​to obtain an average illumination intensity value of the projection space; The processing module (202) is further used to determine, according to the average illumination intensity value, a projection brightness range corresponding to the average illumination intensity value in a preset projection brightness library, wherein the preset projection brightness library includes a correspondence between illumination intensity values ​​and projection brightness ranges; The acquisition module (201) is also used to acquire the vision parameters of each viewing user; The processing module (202) is further used to determine the target projection brightness within the projection brightness range according to the vision parameter; The processing module (202) is further configured to generate a target projection image according to the target projection brightness.

6. An electronic device, characterized in that: The electronic device (300) comprises a processor (301), a memory (305), a user interface (303) and a network interface (304), wherein the memory (305) is used to store instructions, the user interface (303) and the network interface (304) are used to communicate with other devices, and the processor (301) is used to execute the instructions stored in the memory (305) so that the electronic device (300) executes the method according to any one of claims 1 to 4.

7. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores instructions, and when the instructions are executed, the method according to any one of claims 1 to 4 is performed.

Images