Information processing method and device

Abstract

The invention discloses an information processing method and device, and belongs to the technical field of electronic equipment. The information processing method comprises the steps of determining a first task according to first information input by a user; according to a model deployment table, at least two pieces of target equipment for processing the first task are determined in the at least two pieces of electronic equipment, and the model deployment table comprises a processing model deployed by each piece of electronic equipment and a capability rating of each processing model when the processing model runs in the deployed electronic equipment; and controlling the at least two target devices to process the first information.

Description

Technical Field

[0001] The present application belongs to the technical field of electronic equipment, and specifically relates to an information processing method and device thereof. Background Art

[0002] With the rapid development of artificial intelligence, large models that can provide users with rich intelligent services have been proposed. The above large models need to be deployed on electronic devices for use.

[0003] However, large models require relatively high computing power on the end of electronic devices. Many electronic devices do not have the hardware foundation to deploy such large models, making it impossible for large models to provide users with rich intelligent services. Summary of the invention

[0004] The purpose of the embodiments of the present application is to provide an information processing method and device thereof, which can solve the problem that many electronic devices do not have the hardware foundation for deploying the above-mentioned large model, making it impossible for the large model to provide users with rich intelligent services.

[0005] In a first aspect, an embodiment of the present application provides an information processing method, including: determining a first task based on first information input by a user; determining at least two target devices for processing the first task in at least two electronic devices based on a model deployment table, the model deployment table including a processing model deployed by each electronic device and a capability rating of each processing model when running in the deployed electronic device; and controlling at least two target devices to process the first information.

[0006] In a second aspect, an embodiment of the present application provides an information processing device, comprising: a determination module, used to determine a first task based on first information input by a user; a search module, used to determine at least two target devices for processing the first task in at least two electronic devices based on a model deployment table, the model deployment table including a processing model deployed by each electronic device and a capability rating of each processing model when running in the deployed electronic device; and a control module, used to control at least two target devices to process the first information.

[0007] In a third aspect, an embodiment of the present application provides an electronic device, which includes a processor and a memory, wherein the memory stores programs or instructions that can be run on the processor, and when the programs or instructions are executed by the processor, the steps of the method of the first aspect are implemented.

[0008] In a fourth aspect, an embodiment of the present application provides a readable storage medium, on which a program or instruction is stored, and when the program or instruction is executed by a processor, the steps of the method of the first aspect are implemented.

[0009] In a fifth aspect, an embodiment of the present application provides a chip, the chip including a processor and a communication interface, the communication interface and the processor are coupled, and the processor is used to run programs or instructions to implement the method of the first aspect.

[0010] In a sixth aspect, an embodiment of the present application provides a computer program product, which is stored in a storage medium and is executed by at least one processor to implement the method of the first aspect.

[0011] In an embodiment of the present application, an information processing method is proposed. By running the above information processing method, a first task can be determined based on the first information, and at least two target devices for processing the first task can be determined from at least two electronic devices using a model deployment table, wherein the target device is an electronic device on which a processing model is deployed. Therefore, the processing model deployed in the target device can be used to process the first information, so that electronic devices that do not have a large model deployed can also provide users with rich intelligent services. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Figure 1 It is one of the flowcharts of the information processing method provided by some embodiments of the present application;

[0013] Figure 2 is a connection diagram of a scheduling network provided in some embodiments of the present application;

[0014] Figure 3 This is the second flowchart of the information processing method provided by some embodiments of the present application;

[0015] Figure 4 It is a flowchart of a user initiating a large model task and executing the task according to the large model capability priority matrix of the device provided in some embodiments of the present application;

[0016] Figure 5 It is a flowchart of monitoring device load, user behavior, etc. and dynamically adjusting the rating of large model capabilities according to some embodiments of the present application;

[0017] Figure 6 is a schematic block diagram of an information processing device provided by some embodiments of the present application;

[0018] Figure 7 is a schematic block diagram of an electronic device in an embodiment of the present application;

[0019] Figure 8 It is a schematic diagram of the hardware structure of the electronic device in the embodiment of the present application. DETAILED DESCRIPTION

[0020] The embodiments of the present application will be described in detail below. Examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present application, and should not be construed as limitations on the present application. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of the present application.

[0021] The term "first" or "second" in the specification and claims of this application may include one or more of the features explicitly or implicitly. In the description of this application, unless otherwise specified, "plurality" means two or more. In addition, "and / or" in the specification and claims means at least one of the connected objects, and the character " / " generally means that the objects connected before and after are in an "or" relationship.

[0022] In the description of this application, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0023] The information processing method and device provided by the embodiments of the present application are described in detail below through specific embodiments and their application scenarios in conjunction with the accompanying drawings.

[0024] In some embodiments of the present application, Figure 1 As shown, an information processing method is proposed, comprising:

[0025] Step 102: determine a first task according to first information input by a user.

[0026] In this embodiment, the first task can be understood as a task of large model processing.

[0027] Exemplarily, when the first information is “help me identify the text in this picture and summarize the main points”, the first task is a picture recognition task and a text summarization task.

[0028] Exemplarily, when the first information may be “help me summarize these 10 documents”, the first task is a text summarization task.

[0029] In some embodiments of the present application, before determining the first task according to the first information input by the user, the method further includes: receiving a first input for entering the first information.

[0030] In some embodiments of the present application, the first information is information that the user wants to process using the large model.

[0031] For example, the first information may be “help me identify the text in this picture and summarize the key points.”

[0032] Exemplarily, the first information may be “help me summarize these 10 documents”.

[0033] In some embodiments of the present application, the first input may be a voice input.

[0034] Exemplarily, the first input is a voice message of “help me identify the text in this picture and summarize the main points”.

[0035] In some embodiments of the present application, the first input may be text input, such as typing the text “Help me identify the text in this picture and summarize the main points” through an electronic device.

[0036] Step 104, determining at least two target devices for processing the first task in at least two electronic devices according to the model deployment table, wherein the model deployment table includes the processing models deployed by each electronic device and the capability rating of each processing model when running in the deployed electronic device.

[0037] Exemplarily, the electronic device may be a mobile phone, a smart watch, a tablet computer, or other device deployed with the processing model.

[0038] Among them, the processing model is also the big model mentioned in this application, and the big model can be a neural network model.

[0039] Among them, the capability rating can be understood as the evaluation result obtained by evaluating the processing capability of the processing model when the processing model is running in the deployed electronic device.

[0040] Step 106: Control at least two target devices to process the first information.

[0041] In an embodiment of the present application, an information processing method is proposed. By running the above information processing method, a first task can be determined based on the first information, and at least two target devices for processing the first task can be determined from at least two electronic devices using a model deployment table, wherein the target device is an electronic device on which a processing model is deployed. Therefore, the processing model deployed in the target device can be used to process the first information, so that electronic devices that do not have a large model deployed can also provide users with rich intelligent services.

[0042] In addition, for electronic devices with relatively weak hardware computing power, they cannot be deployed to provide users with rich intelligent services. By adopting the information processing method proposed in this application, mid-range electronic devices and low-end electronic devices can also provide users with rich intelligent services.

[0043] In some embodiments of the present application, the first information is identified to obtain the processing intention of the user, and the first task is determined according to the processing intention of the user.

[0044] For example, when the first information is "Help me identify the text in this picture and summarize the main points", it can be recognized that the user's intention is image recognition, and text summary is performed based on the result of image recognition. Based on this, the first task can be divided into image recognition task and text summary task.

[0045] In some embodiments of the present application, a first task includes a first subtask and a second subtask, at least two target devices include a first device and a second device, and controlling at least two target devices to process the first information specifically includes: sending the first information to the first device, and controlling the first device to process the first information when executing the first subtask to obtain a first execution result; sending the first execution result to the second device, and controlling the second device to process the first execution result when executing the second subtask to obtain a second execution result.

[0046] In this embodiment, when the first task includes a first subtask and a second subtask, the first device can be used to execute the first subtask, and the second device can be used to execute the second subtask, wherein the first device processes the first information when executing the first subtask to obtain a first execution result, and the first execution result serves as input when the second device executes the second subtask, so that the second device obtains the second execution result after completing the execution of the second subtask.

[0047] In this process, the first task can be divided into a first subtask and a second subtask, and the first information can be processed by using the first device and the second device to respectively execute the first subtask and the second subtask.

[0048] Obviously, in this process, the processing models deployed on different electronic devices can be used to implement more complex intelligent services, thereby providing users with rich intelligent services.

[0049] Exemplarily, when the first information is "Help me identify the text in this picture and summarize the main points", it can be recognized that the user's intention is image recognition, and text summary is performed based on the result of image recognition. Based on this, the first task can be divided into image recognition task and text summary task, among which the image recognition task is also the first subtask, and the text summary task is also the second subtask.

[0050] Based on this, the picture is input into the first device as the first information, so that the first device can perform the picture recognition task to identify the text in the picture, wherein the text in the picture is identified, which is the first execution result in this application, and the text in the picture is used as the input of the second device, so that when the second device performs the text summary task, a summary result is obtained, wherein the summary result is also the second execution result in this application.

[0051] In some embodiments of the present application, at least two target devices include a third device and a fourth device, and the information processing method also includes: evaluating the first task to obtain an evaluation result; controlling at least two target devices to process the first information, specifically including: when the evaluation result is the first evaluation result, sending the second information in the first information to the third device, and controlling the third device to process the second information when executing the first task to obtain a third execution result; sending the third information to the fourth device, and controlling the fourth device to process the third information when executing the first task to obtain a fourth execution result, where the third information is information in the first information other than the second information; and obtaining the execution result of the first information based on the third execution result and the fourth execution result.

[0052] In this embodiment, the first task is evaluated to assess whether the same task can be executed simultaneously by multiple devices, so as to speed up the processing efficiency of the first information.

[0053] Specifically, if the evaluation result is the first evaluation result, it is considered that the first task can be split into multiple tasks that can be executed simultaneously. At this time, the second information in the first information is sent to the third device, and the third information is sent to the fourth device, so that the third device and the fourth device can execute the first task and obtain corresponding execution results respectively, that is, the third execution result and the fourth execution result.

[0054] In this process, the processing efficiency of the first information can be improved.

[0055] For example, when the first information is “help me summarize these 10 documents”, the first task is “summarize these 10 documents”. By evaluating the task of “summarize these 10 documents” and determining that the evaluation result is the first evaluation result, the first information can be divided into second information and third information, where the second information is “help me summarize these 6 documents” and the third information is “help me summarize these 4 documents”.

[0056] In some embodiments of the present application, evaluating the first task can be understood as determining the task level of the first task. Based on this, when the evaluation result is the first evaluation result, it is considered that the task level of the first task is 2, and two devices are required to process the first information simultaneously.

[0057] Based on this, "Help me summarize these 6 documents" can be sent to a third device for processing by the third device. At the same time, "Help me summarize these 4 documents" can be sent to a fourth device for processing by the fourth device. By summarizing the execution results of the third device and the fourth device, the execution result of the first information can be obtained.

[0058] In some embodiments of the present application, the information processing method also includes: obtaining the processing model deployed by each electronic device, obtaining the static computing power of the electronic device when the processing model deployed in each electronic device is running, and obtaining the operating scenario and load information of the electronic device when the processing model deployed in each electronic device is running; determining the capability rating of each processing model when it is running in the deployed electronic device based on the static computing power, operating scenario and load information; determining the model deployment table based on the electronic device, the processing model deployed by the electronic device, and the capability rating of each processing model when it is running in the deployed electronic device.

[0059] Exemplarily, when adding a personal device via Bluetooth, wireless network communication technology (Wi-Fi) or other means, device information is added, wherein the device information includes a processing model deployed by each electronic device and hardware information of each electronic device.

[0060] Exemplarily, as shown in Table 1, the device information includes electronic device A and electronic device B.

[0061] Table 1

[0062] Device Information Electronic equipment A Electronic equipment B CPU Model A1 B1 CPU Model A2 B2 Supported large model capabilities Text summary, text image Text Summary Additional Information … …

[0063] In this embodiment, if Figure 2 As shown, a scheduling network between the scheduling center and different electronic devices can be pre-constructed, and a model deployment table can be constructed based on the constructed scheduling network.

[0064] Specifically, the dispatch network includes mobile phones, watches, tablet computers and other electronic devices, wherein the mobile phones, watches, tablet computers and other electronic devices interact through the cloud, wherein the mobile phones serve as dispatch centers.

[0065] Among them, static computing power can be understood as the computing power of electronic devices per unit power consumption when the processing model is running.

[0066] Specifically, static computing power is evaluated based on the device's hardware parameters, CPU, GPU performance, and lab data, where the CPU and GPU speed and power consumption are measured when running the end-side model.

[0067] Specifically, the calculation formula of static computing power is: X = FuncA (CPU, GPU, power consumption), where FuncA (CPU, GPU, power consumption) represents a function with CPU, GPU, and power consumption as input, and X represents static computing power, which is specifically defined as follows:

[0068]

[0069] Wherein, ∑ is the summation symbol, i represents the i-th CPU, j represents the j-th GPU, and the meanings of each parameter are shown in Table 2.

[0070] Table 2

[0071]

[0072] Among them, the central processing unit (CPU) is the computing and control core of the computer system and the final execution unit for information processing and program running.

[0073] Graphics Processing Unit (GPU), also known as display core, visual processor, display chip, is a microprocessor specially used to perform image and graphics related calculations on personal computers, workstations, game consoles and some mobile devices (such as tablets, smart phones, etc.).

[0074] As shown in Table 3, the operating scenarios are divided into heavy usage scenarios, moderate usage, light usage, and idle state.

[0075] Table 3

[0076]

[0077] In some embodiments of the present application, the device load of each electronic device can be determined based on the operating scenario and load information.

[0078] Specifically, device load Y = function B (scenario, CPU occupancy, GPU occupancy, temperature, power), function B (scenario, CPU occupancy, GPU occupancy, temperature, power) represents a function with scenario, CPU occupancy, GPU occupancy, temperature, and power as inputs, and Y is the device load, which is specifically defined as follows:

[0079] Y=U cpu ×W scpu +U gpu ×W sgpu +Wt×(70-T)+W b ×(100-B)

[0080] The meaning of each parameter is shown in Table 4.

[0081] Table 4

[0082]

[0083]

[0084] In some embodiments of the present application, the capability of each processing model when running in a deployed electronic device is represented by P, then P=functionC(static computing power X, device load Y), where functionC(static computing power X, device load Y) represents a function with static computing power X and device load Y as inputs.

[0085] P=normalize10(X)-normalize5(Y)

[0086] The meaning of each parameter is shown in Table 5.

[0087] Table 5

[0088]

[0089] Based on this, the capability rating of each processing model when running in the deployed electronic equipment is represented by S, then:

[0090]

[0091] In some embodiments of the present application, as shown in Table 6, the model deployment table is stored in the form of a table.

[0092] Table 6

[0093] Large model capabilities Device A Device B Device C Text Summary 1 (best) 2 (better) 3(Normal) Image recognition 3 2 1 Vincent Figure 2 1 -1 (Not supported)

[0094] In some embodiments of the present application, the information processing method also includes: obtaining the current usage scenario of each electronic device and the current load information of each electronic device; and updating the capability rating in the model deployment table based on the current usage scenario of each electronic device and the current load information of each electronic device.

[0095] In this embodiment, the current usage scenario of each electronic device and the current load information of each electronic device are obtained so that the capability rating in the model deployment table is updated according to the current usage scenario of each electronic device and the current load information of each electronic device. Therefore, the capability rating can be dynamically updated according to the real-time operating status of each electronic device, thereby ensuring the accuracy of the model deployment table.

[0096] In some embodiments of the present application, the information processing method also includes: when a change in load information of the fifth device and / or a change in the usage scenario of the fifth device is detected, obtaining a target processing task processed by the fifth device and a capability rating corresponding to the fifth device, the fifth device being one of at least two target devices, and the target processing task being the first task processed by the fifth device; searching for a sixth device based on the capability rating corresponding to the fifth device and the target processing task processed by the fifth device; when the sixth device is found, sending the first processing result of the target processing task processed by the fifth device to the sixth device for processing by the sixth device; when the sixth device is not found, outputting a reminder message; wherein the reminder message is used to remind the user to suspend execution of the target processing task or continue execution of the target processing task.

[0097] In this embodiment, if a change in load information and / or a change in the usage scenario of one of at least two target devices is detected, it is considered that the target device performing the first task may not be the optimal electronic device. At this time, an attempt is made to find a sixth device to replace the fifth device, and when the sixth device is found, the first processing result of the fifth device is used as the input of the sixth device for the sixth device to continue processing. In this process, the advantages of multiple electronic devices can be fully utilized to reduce problems such as limited capacity of a single device, large model or slow response when the load is large.

[0098] In some embodiments of the present application, Figure 3 As shown, the information processing method includes:

[0099] Step 302, when the device is connected, register the device to the dispatch center, add the device information and the supported large model capabilities.

[0100] Among them, the supported large model capabilities are also the deployed processing models in this application.

[0101] Step 304, device hierarchical modeling, calculates the device's large model capability priority matrix based on the device's static computing power and real-time load.

[0102] Among them, the large model capability priority matrix is ​​also the model deployment table in this application.

[0103] Step 306: The user initiates a large model task, and the task is executed according to the large model capability priority matrix of the device.

[0104] Step 308, monitor device load, user behavior, etc., and dynamically adjust the large model capability rating.

[0105] Among them, dynamically adjusting the large model capability rating is the capability rating in the updated model deployment table in this application.

[0106] Step 310, whether the running large model task needs to be processed, if the judgment result is yes, execute step 312, if the judgment result is no, end.

[0107] Step 312, the terminal side central control processing task continues.

[0108] Exemplarily, when the load or user usage changes during the device running the large model task, if the user opens the game on the device at this time, the end-side central control will search for an executable sixth device based on the current device task type and rating. If an available sixth device is found, the end-side central control will save the intermediate results of the current device operation to the central control, and the dispatch center will save the output intermediate results, and then use the continuation type prompt word template package to convert the task into a task continued by the sixth device, and dispatch it to the sixth device for execution. If there is no alternative sixth service, the user will be prompted to continue the large model task or interrupt the execution of the large model task according to the task emergency situation. The interrupted task will be resumed after the user exits the game.

[0109] Among them, Figure 4 As shown, in step 306, the user initiates a large model task, and the task is executed according to the large model capability priority matrix of the device, specifically including:

[0110] Step 402: When a user uses the large model capability, the dispatch center first identifies the user's intention, decomposes the task, and rates the task.

[0111] Step 404: Scheduling of tasks for the large model capability of the terminal-side central control.

[0112] Step 406, summarize the results of each device's large model.

[0113] Among them, Figure 5As shown, step 308 monitors device load, user behavior, etc., and dynamically adjusts the large model capability rating, specifically including:

[0114] Step 502, when adding a device, register the relevant load status and scene monitoring according to the large model capability.

[0115] Specifically, when adding a device to the end-side central control, register related device scene monitoring or device load status monitoring according to the large model capability of the device.

[0116] When these indicators change, the end-side central control will dynamically adjust the classification of the large model scene of the associated device. Among them, scene monitoring includes the following user scenarios:

[0117] (1) When the user is using an application, such as playing games or taking photos on the device, large model tasks should be avoided from being scheduled to the device.

[0118] (2) Based on the user's application usage habits, application prediction is performed to determine which applications the user may want to open. For example, after get off work, the user may play games or perform audio-visual entertainment. In this scenario, the large model task is not suitable for scheduling to the device, and an interruption is likely to occur.

[0119] (3) Combined with the user's location-based services (LBS) scenario, for example, a user may use a tablet as the main entertainment device when at home. Large model tasks can be scheduled to idle devices such as mobile phones first.

[0120] Among them, the key indicators for monitoring the equipment load status are as follows:

[0121] (1) CPU usage (2) GPU usage (3) Memory (4) Power (5) Temperature.

[0122] Step 504: the state of the large model of the equipment changes, and the scene classification and load classification processes are entered in sequence.

[0123] Step 506, the device scene changes to determine whether the associated large model capabilities need to be adjusted. If the judgment result is yes, execute step 508, if the judgment result is no, end.

[0124] Step 508, hierarchical evaluation based on the device scenario big model.

[0125] Exemplarily, Table 7 shows a specific strategy based on the hierarchical evaluation of the device scenario big model. As shown in Table 7, when there is a corresponding event, the rating of the associated big model is lowered.

[0126] Table 7

[0127]

[0128]

[0129] Step 510, the equipment real-time load large model hierarchically evaluates the equipment scene changes to determine whether the associated large model capabilities need to be adjusted. If the judgment result is yes, execute step 512, if the judgment result is no, end.

[0130] Step 512: perform a hierarchical evaluation of the equipment real-time load model.

[0131] Exemplarily, Table 8 shows a specific strategy for the hierarchical evaluation of the large model of real-time load of the equipment. As shown in Table 8, when there is a corresponding event, the rating of the associated large model is reduced.

[0132] Table 8

[0133]

[0134] The information processing method provided in the embodiment of the present application can be executed by an information processing device. In the embodiment of the present application, the information processing device provided in the embodiment of the present application is described by taking the information processing device executing the information processing method as an example.

[0135] In some embodiments of the present application, Figure 6 As shown, an information processing device 600 is proposed, including: a determination module 602, used to determine a first task according to first information input by a user; a search module 604, used to determine at least two target devices for processing the first task in at least two electronic devices according to a model deployment table, the model deployment table including a processing model deployed by each electronic device and a capability rating of each processing model when running in the deployed electronic device; a control module 606, used to control at least two target devices to process the first information.

[0136] In an embodiment of the present application, a first task can be determined based on the first information, and a model deployment table can be used to determine at least two target devices for processing the first task from at least two electronic devices, wherein the target device is an electronic device on which a processing model is deployed. Therefore, the processing model deployed in the target device can be used to process the first information, so that electronic devices that do not have a large model deployed can also provide users with rich intelligent services.

[0137] In some embodiments of the present application, the first task includes a first subtask and a second subtask, and the at least two target devices include a first device and a second device. The control module 606 is specifically used to: send the first information to the first device, and control the first device to process the first information when executing the first subtask to obtain a first execution result; send the first execution result to the second device, and control the second device to process the first execution result when executing the second subtask to obtain a second execution result.

[0138] In some embodiments of the present application, at least two target devices include a third device and a fourth device, and the search module 604 is further used to: evaluate the first task to obtain an evaluation result; the control module 606 is specifically used to: when the evaluation result is the first evaluation result, send the second information in the first information to the third device, and control the third device to process the second information when executing the first task to obtain a third execution result; send the third information to the fourth device, and control the fourth device to process the third information when executing the first task to obtain a fourth execution result, where the third information is the information in the first information except the second information; and obtain the execution result of the first information based on the third execution result and the fourth execution result.

[0139] In some embodiments of the present application, the search module 604 is also used to: obtain the processing model deployed by each electronic device, obtain the static computing power of the electronic device when the processing model deployed in each electronic device is running, and obtain the operating scenario and load information of the electronic device when the processing model deployed in each electronic device is running; determine the capability rating of each processing model when it is running in the deployed electronic device based on the static computing power, operating scenario and load information; determine the model deployment table based on the processing models deployed by the electronic device and the capability rating of each processing model when it is running in the deployed electronic device.

[0140] In some embodiments of the present application, the determination module 602 is also used to: obtain the current usage scenario of each electronic device and the current load information of each electronic device; and update the capability rating in the model deployment table based on the current usage scenario of each electronic device and the current load information of each electronic device.

[0141] In some embodiments of the present application, the control module 606 is also used to: upon detecting a change in the load information of the fifth device and / or a change in the usage scenario of the fifth device, obtain a target processing task processed by the fifth device and a capability rating corresponding to the fifth device, the fifth device being one of at least two target devices, and the target processing task being the first task processed by the fifth device; search for a sixth device based on the capability rating corresponding to the fifth device and the target processing task processed by the fifth device; when the sixth device is found, send the first processing result of the target processing task processed by the fifth device to the sixth device for processing by the sixth device; when the sixth device is not found, output a reminder message; wherein the reminder message is used to remind the user to suspend execution of the target processing task or continue execution of the target processing task.

[0142] The information processing device in the embodiment of the present application can be an electronic device, or a component in the electronic device, such as an integrated circuit or a chip. The electronic device can be a terminal, or it can be other devices other than a terminal. Exemplarily, the electronic device can be a mobile phone, a tablet computer, a laptop computer, a PDA, a vehicle-mounted electronic device, a mobile Internet device (Mobile Internet Device, MID), an augmented reality (augmented reality, AR) / virtual reality (virtual reality, VR) device, a robot, a wearable device, an ultra-mobile personal computer (ultra-mobile personal computer, UMPC), a netbook or a personal digital assistant (personal digital assistant, PDA), etc., and can also be a server, a network attached storage (Network Attached Storage, NAS), a personal computer (personal computer, PC), a television (television, TV), a teller machine or a self-service machine, etc., which is not specifically limited in the embodiment of the present application.

[0143] The information processing device in the embodiment of the present application may be a device having an operating system. The operating system may be an Android operating system, an IOS operating system, or other possible operating systems, which are not specifically limited in the embodiment of the present application.

[0144] The information processing device provided in the embodiment of the present application can achieve the following Figure 1 The various processes implemented by the information processing method embodiment can achieve the same technical effect. To avoid repetition, they will not be described here.

[0145] like Figure 7As shown, an embodiment of the present application also provides an electronic device 700, including a processor 702 and a memory 704, wherein the memory 704 stores programs or instructions that can be executed on the processor 702, and when the program or instructions are executed by the processor 702, the various steps of the above-mentioned information processing method embodiment are implemented, and the same technical effect can be achieved. To avoid repetition, they are not described here.

[0146] It should be noted that the electronic devices in the embodiments of the present application include the above-mentioned mobile electronic devices and non-mobile electronic devices.

[0147] Figure 8 A schematic diagram of the hardware structure of an electronic device to implement an embodiment of the present application.

[0148] like Figure 8 As shown, the electronic device 800 includes but is not limited to: a radio frequency unit 801, a network module 802, an audio output unit 803, an input unit 804, a sensor 805, a display unit 806, a user input unit 807, an interface unit 808, a memory 809, and a processor 810 and other components.

[0149] Those skilled in the art will appreciate that the electronic device 800 may also include a power source (such as a battery) for supplying power to each component, and the power source may be logically connected to the processor 810 through a power management system, thereby implementing functions such as managing charging, discharging, and power consumption management through the power management system. Figure 8 The electronic device structure shown in the figure does not constitute a limitation on the electronic device. The electronic device may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently, which will not be described in detail here.

[0150] In some embodiments of the present application, the processor 810 is used to: determine a first task based on first information input by a user; determine at least two target devices for processing the first task in at least two electronic devices based on a model deployment table, the model deployment table including a processing model deployed by each electronic device and a capability rating of each processing model when running in the deployed electronic device; and control at least two target devices to process the first information.

[0151] In some embodiments of the present application, the first task includes a first subtask and a second subtask, and the at least two target devices include a first device and a second device. The processor 810 is specifically used to: send the first information to the first device, and control the first device to process the first information when executing the first subtask to obtain a first execution result; send the first execution result to the second device, and control the second device to process the first execution result when executing the second subtask to obtain a second execution result.

[0152] In some embodiments of the present application, at least two target devices include a third device and a fourth device, and the processor 810 is also used to: evaluate the first task to obtain an evaluation result; the processor 810 is specifically used to, when the evaluation result is the first evaluation result, send the second information in the first information to the third device, and control the third device to process the second information when executing the first task to obtain a third execution result; send the third information to the fourth device, and control the fourth device to process the third information when executing the first task to obtain a fourth execution result, where the third information is information in the first information other than the second information; and obtain the execution result of the first information based on the third execution result and the fourth execution result.

[0153] In some embodiments of the present application, the processor 810 is also used to: obtain the processing model deployed by each electronic device, obtain the static computing power of the electronic device when the processing model deployed in each electronic device is running, and obtain the operating scenario and load information of the electronic device when the processing model deployed in each electronic device is running; determine the capability rating of each processing model when it is running in the deployed electronic device based on the static computing power, operating scenario and load information; determine the model deployment table based on the processing models deployed by the electronic device and the capability rating of each processing model when it is running in the deployed electronic device.

[0154] In some embodiments of the present application, the processor 810 is also used to: obtain the current usage scenario of each electronic device and the current load information of each electronic device; and update the capability rating in the model deployment table based on the current usage scenario of each electronic device and the current load information of each electronic device.

[0155] In some embodiments of the present application, the processor 810 is also used to obtain a target processing task processed by the fifth device and a capability rating corresponding to the fifth device when a change in load information of the fifth device and / or a change in the usage scenario of the fifth device is detected, the fifth device being one of at least two target devices, and the target processing task being the first task processed by the fifth device; searching for a sixth device based on the capability rating corresponding to the fifth device and the target processing task processed by the fifth device; when the sixth device is found, sending the first processing result of the target processing task processed by the fifth device to the sixth device for processing by the sixth device; when the sixth device is not found, outputting a reminder message; wherein the reminder message is used to remind the user to suspend execution of the target processing task or continue execution of the target processing task.

[0156] In an embodiment of the present application, a first task can be determined based on the first information, and a model deployment table can be used to determine at least two target devices for processing the first task from at least two electronic devices, wherein the target device is an electronic device on which a processing model is deployed. Therefore, the processing model deployed in the target device can be used to process the first information, so that electronic devices that do not have a large model deployed can also provide users with rich intelligent services.

[0157] It should be understood that in the embodiment of the present application, the input unit 804 may include a graphics processor (Graphics Processing Unit, GPU) 8041 and a microphone 8042, and the graphics processor 8041 processes the image data of the static picture or video obtained by the image capture device (such as a camera) in the video capture mode or the image capture mode. The display unit 806 may include a display panel 8061, and the display panel 8061 may be configured in the form of a liquid crystal display, an organic light emitting diode, etc. The user input unit 807 includes a touch panel 8071 and at least one of other input devices 8072. The touch panel 8071 is also called a touch screen. The touch panel 8071 may include two parts: a touch detection device and a touch controller. Other input devices 8072 may include, but are not limited to, a physical keyboard, function keys (such as volume control keys, switch keys, etc.), a trackball, a mouse, and a joystick, which will not be repeated here.

[0158] The memory 809 can be used to store software programs and various data. The memory 809 may mainly include a first storage area for storing programs or instructions and a second storage area for storing data, wherein the first storage area may store an operating system, an application program or instructions required for at least one function (such as a sound playback function, an image playback function, etc.), etc. In addition, the memory 809 may include a volatile memory or a non-volatile memory, or the memory 809 may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), a static random access memory (SRAM), a dynamic random access memory (DRAM), a synchronous dynamic random access memory (SDRAM), a double data rate synchronous dynamic random access memory (DDRSDRAM), an enhanced synchronous dynamic random access memory (ESDRAM), a synchronous link dynamic random access memory (SLDRAM) and a direct memory bus random access memory (DRRAM). The memory 809 in the embodiment of the present application includes but is not limited to these and any other suitable types of memory.

[0159] The processor 810 may include one or more processing units; optionally, the processor 810 integrates an application processor and a modem processor, wherein the application processor mainly processes operations related to an operating system, a user interface, and application programs, and the modem processor mainly processes wireless communication signals, such as a baseband processor. It is understandable that the modem processor may not be integrated into the processor 810.

[0160] An embodiment of the present application also provides a readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, the various processes of the above-mentioned information processing method embodiment are implemented and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0161] The processor is the processor in the electronic device in the above embodiment. The readable storage medium includes a computer readable storage medium, such as a computer read-only memory ROM, a random access memory RAM, a magnetic disk or an optical disk.

[0162] An embodiment of the present application further provides a chip, which includes a processor and a communication interface, wherein the communication interface and the processor are coupled, and the processor is used to run programs or instructions to implement the various processes of the above-mentioned information processing method embodiment, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0163] It should be understood that the chip mentioned in the embodiments of the present application can also be called a system-level chip, a system chip, a chip system or a system-on-chip chip, etc.

[0164] An embodiment of the present application provides a computer program product, which is stored in a storage medium. The program product is executed by at least one processor to implement the various processes of the above-mentioned information processing method embodiment and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0165] It should be noted that, in this article, the terms "comprise", "include" or any other variants thereof are intended to cover non-exclusive inclusion, so that the process, method, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the statement "including one" do not exclude the presence of other identical elements in the process, method, article or device including the element. In addition, it should be pointed out that the scope of the methods and devices in the embodiments of the present application is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in reverse order according to the functions involved, for example, the described method may be performed in an order different from that described, and various steps may also be added, omitted, or combined. In addition, the features described with reference to certain examples may be combined in other examples.

[0166] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the embodiments of the present application are essentially or partly contributed to the prior art can be embodied in the form of a computer software product, which is stored in a storage medium (such as ROM / RAM, a disk, an optical disk), and includes a number of instructions for a terminal (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods of each embodiment of the present application.

[0167] The embodiments of the present application are described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present application, ordinary technicians in this field can also make many forms without departing from the purpose of the present application and the scope of protection of the claims, all of which are within the protection of the present application.

Claims

1. An information processing method, characterized in that: include: determining a first task according to first information input by a user; Determining at least two target devices for processing the first task among at least two electronic devices according to a model deployment table, wherein the model deployment table includes a processing model deployed by each of the electronic devices and a capability rating of each of the processing models when running in the deployed electronic devices; The at least two target devices are controlled to process the first information.

2. The information processing method according to claim 1, characterized in that: The first task includes a first subtask and a second subtask, the at least two target devices include a first device and a second device, and controlling the at least two target devices to process the first information specifically includes: sending the first information to the first device, and controlling the first device to process the first information when executing the first subtask to obtain a first execution result; The first execution result is sent to the second device, and the second device is controlled to process the first execution result when executing the second subtask to obtain a second execution result.

3. The information processing method according to claim 1, characterized in that: The at least two target devices include a third device and a fourth device, and the information processing method further includes: Evaluating the first task to obtain an evaluation result; The controlling the at least two target devices to process the first information specifically includes: When the evaluation result is the first evaluation result, sending the second information in the first information to the third device, and controlling the third device to process the second information when executing the first task to obtain a third execution result; sending third information to the fourth device, and controlling the fourth device to process the third information when executing the first task to obtain a fourth execution result, wherein the third information is information in the first information except the second information; An execution result of the first information is obtained based on the third execution result and the fourth execution result.

4. The information processing method according to any one of claims 1 to 3, characterized in that: The information processing method further includes: Obtaining a processing model deployed by each of the electronic devices, obtaining the static computing power of the electronic device when the processing model deployed in each of the electronic devices is running, and obtaining the operating scenario and load information of the electronic device when the processing model deployed in each of the electronic devices is running; Determine a capability rating of each of the processing models when running in the deployed electronic device based on the static computing power, the operating scenario, and the load information; The model deployment table is determined based on the processing models deployed by the electronic device and the capability rating of each of the processing models when running in the deployed electronic device.

5. The information processing method according to any one of claims 1 to 3, characterized in that: The information processing method further includes: When a change in load information of a fifth device and / or a change in a usage scenario of the fifth device is detected, obtaining a target processing task processed by the fifth device and a capability rating corresponding to the fifth device, the fifth device being one of the at least two target devices, and the target processing task being the first task processed by the fifth device; Finding a sixth device based on the capability rating corresponding to the fifth device and the target processing task processed by the fifth device; In the case where the sixth device is found, sending the first processing result of the fifth device processing the target processing task to the sixth device for processing by the sixth device; If the sixth device is not found, outputting a reminder message; The reminder information is used to remind the user to suspend the execution of the target processing task or to continue the execution of the target processing task.

6. An information processing device, characterized in that: include: A determination module, used to determine a first task according to first information input by a user; a search module, configured to determine at least two target devices for processing the first task from among at least two electronic devices according to a model deployment table, wherein the model deployment table includes a processing model deployed by each of the electronic devices and a capability rating of each of the processing models when running in the deployed electronic devices; A control module is used to control the at least two target devices to process the first information.

7. The information processing device according to claim 6, characterized in that: The first task includes a first subtask and a second subtask, the at least two target devices include a first device and a second device, and the control module is specifically configured to: sending the first information to the first device, and controlling the first device to process the first information when executing the first subtask to obtain a first execution result; The first execution result is sent to the second device, and the second device is controlled to process the first execution result when executing the second subtask to obtain a second execution result.

8. The information processing device according to claim 6, characterized in that: The at least two target devices include a third device and a fourth device, and the search module is further used for: Evaluating the first task to obtain an evaluation result; The control module is specifically used for: When the evaluation result is the first evaluation result, sending the second information in the first information to the third device, and controlling the third device to process the second information when executing the first task to obtain a third execution result; sending third information to the fourth device, and controlling the fourth device to process the third information when executing the first task to obtain a fourth execution result, wherein the third information is information in the first information except the second information; An execution result of the first information is obtained based on the third execution result and the fourth execution result.

9. The information processing device according to any one of claims 6 to 8, characterized in that: The search module is also used for: Obtaining a processing model deployed by each of the electronic devices, obtaining the static computing power of the electronic device when the processing model deployed in each of the electronic devices is running, and obtaining the operating scenario and load information of the electronic device when the processing model deployed in each of the electronic devices is running; Determine a capability rating of each of the processing models when running in the deployed electronic device based on the static computing power, the operating scenario, and the load information; The model deployment table is determined based on the processing models deployed by the electronic device and the capability rating of each of the processing models when running in the deployed electronic device.

10. The information processing device according to any one of claims 6 to 8, characterized in that: The control module is also used for: When a change in load information of a fifth device and / or a change in a usage scenario of the fifth device is detected, obtaining a target processing task processed by the fifth device and a capability rating corresponding to the fifth device, the fifth device being one of the at least two target devices, and the target processing task being the first task processed by the fifth device; Finding a sixth device based on the capability rating corresponding to the fifth device and the target processing task processed by the fifth device; In the case where the sixth device is found, sending the first processing result of the fifth device processing the target processing task to the sixth device for processing by the sixth device; If the sixth device is not found, outputting a reminder message; The reminder information is used to remind the user to suspend the execution of the target processing task or to continue the execution of the target processing task.

Images