Broadcasting method and device based on large model, medium and product

Abstract

The invention provides a broadcasting method and device based on a large model, a medium and a product, and relates to the technical field of broadcasting. The broadcasting method based on the large model comprises the following steps: acquiring broadcast associated data corresponding to a to-be-broadcasted area, wherein the broadcast associated data comprises at least one of environment data and behavior data; broadcast features are extracted through the broadcast associated data, the broadcast features are transmitted to the large model, and the broadcast features comprise at least one of access features, regional features, environment features and target object emotion features; and acquiring broadcast information output by the large model and corresponding to the broadcast features, and executing broadcast operation based on the broadcast information. The broadcast content can be quickly generated, the operation is simple, the flexibility is good, the labor cost is effectively reduced, the change of the broadcast area can be quickly adapted, the timeliness and the flexibility of the broadcast content are effectively ensured, and the user experience is improved.

Description

Technical Field

[0001] The present application relates to the field of broadcast technology, and more specifically, to a broadcast method, device, medium and product based on a large model. Background Art

[0002] In order to quickly realize large-scale message notification and emergency evacuation, broadcasting equipment is often installed in places where a large number of people gather, such as shopping malls, office buildings, and schools. The broadcasting equipment is used to broadcast the content to be conveyed to the broadcasting area where it is located.

[0003] However, existing broadcasting mostly uses manual broadcasting to broadcast information, that is, it is necessary to manually collect data related to the broadcast area, and then write and broadcast the broadcast information based on the data. Broadcasting operations are cumbersome, time-consuming and labor-intensive. As a result, when broadcasting equipment is actually used, fixed broadcast content and schedules are often set, and fixed broadcast content is played according to the schedule, making the broadcast method inflexible and difficult to quickly adapt to changes in the broadcast area, reducing user experience. Summary of the invention

[0004] The embodiments of the present application provide a broadcast method, device, medium and product based on a large model, which can solve the problems of fixed content, lack of flexibility, inability to quickly adapt to changes in broadcast areas, and reduced user experience. To achieve this purpose, the embodiments of the present application provide the following solutions.

[0005] According to one aspect of an embodiment of the present application, a broadcast method based on a large model is provided, the method comprising:

[0006] Collecting broadcast-related data corresponding to the area to be broadcasted, wherein the broadcast-related data includes at least one of environmental data and behavioral data;

[0007] Extracting broadcast features using the broadcast-related data, and transmitting the broadcast features to the big model, wherein the broadcast features include at least one of entry and exit features, regional features, environmental features, and target object emotion features;

[0008] The broadcast information corresponding to the broadcast feature output by the large model is obtained, and a broadcast operation is performed based on the broadcast information.

[0009] In a possible implementation, the collecting broadcast-related data corresponding to the to-be-broadcast area includes:

[0010] Deploy a data collection device in the area to be broadcasted and obtain social media data, wherein the data collection device includes at least one of a camera and a sensor;

[0011] The broadcast associated data is collected using the data collection device and the social media data.

[0012] In a possible implementation, the data collection device includes a camera, and the step of deploying the data collection device in the area to be broadcast includes:

[0013] Installing the cameras at different positions of the area to be broadcasted, and determining monitoring areas of different cameras in the area to be broadcasted according to the distances between the cameras;

[0014] Collecting the broadcast-related data using the data collection device includes:

[0015] The camera is used to obtain behavior data of the target object in the monitoring area, and the behavior data includes at least one of a movement trajectory and entry and exit information.

[0016] In a possible implementation, the extracting broadcast features by using the broadcast associated data includes:

[0017] Acquire coverage information corresponding to the broadcasting device, and determine the regional characteristics of the monitoring area according to the coverage information and the monitoring area;

[0018] The behavior data is used to determine the entry and exit characteristics corresponding to the monitoring area.

[0019] In a possible implementation, the data collection device includes a sensor, and the extracting broadcast features by using the broadcast-related data includes:

[0020] Acquire environmental data collected by the sensor, and obtain state change information from the environmental data using a preset algorithm, wherein the preset algorithm includes a vector machine algorithm;

[0021] The environmental characteristics are determined according to the state change information and the environmental data.

[0022] In a possible implementation, collecting the broadcast-related data using the social media data includes:

[0023] The social media data is extracted, and the behavior data corresponding to the to-be-broadcast area in the social media data is extracted based on a preset filtering method, wherein the preset filtering method includes at least one of keyword filtering, user filtering, and time filtering.

[0024] In a possible implementation, the extracting broadcast features by using the broadcast associated data includes:

[0025] The emotional text in the text corresponding to the behavior data is extracted, and the emotional characteristics of the target object are obtained based on the emotional text.

[0026] According to one aspect of an embodiment of the present application, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the method described above.

[0027] According to one aspect of an embodiment of the present application, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of the method described above are implemented.

[0028] According to one aspect of an embodiment of the present application, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the steps of the method described above are implemented.

[0029] The beneficial effects of the technical solution provided by the embodiment of the present application are:

[0030] The broadcasting method based on the big model provided in the present application includes: collecting broadcast-related data corresponding to the area to be broadcast, the broadcast-related data including at least one of environmental data and behavioral data; extracting broadcast features using the broadcast-related data, and transmitting the broadcast features to the big model; obtaining the broadcast information corresponding to the broadcast features output by the big model, and performing broadcast operations based on the broadcast information. The embodiment of the present application can quickly obtain the change information of the broadcast area and quickly generate corresponding broadcast content according to the change information. It is simple to operate, flexible and can effectively reduce labor costs, realize rapid adaptation to changes in the broadcast area, effectively ensure the timeliness and flexibility of the broadcast content, and improve user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following is a brief introduction to the drawings required for use in describing the embodiments of the present application.

[0032] Figure 1 A flowchart of a large model-based broadcasting method provided in an embodiment of the present application;

[0033] Figure 2 A flowchart of broadcast content generation provided in an embodiment of the present application;

[0034] Figure 3 A flowchart of feature collection and processing provided in an embodiment of the present application;

[0035] Figure 4 This is a structural diagram of the electronic device of this application. DETAILED DESCRIPTION

[0036] The embodiments of the present application are described below in conjunction with the drawings in the present application. It should be understood that the implementation methods described below in conjunction with the drawings are exemplary descriptions for explaining the technical solutions of the embodiments of the present application and do not constitute a limitation on the technical solutions of the embodiments of the present application.

[0037] It will be understood by those skilled in the art that, unless specifically stated, the singular forms "one", "said", and "the" used herein may also include plural forms. It should be further understood that the terms "including" and "comprising" used in the embodiments of the present application refer to that the corresponding features can be implemented as the presented features, information, data, steps, operations, elements and / or components, but do not exclude the implementation of other features, information, data, steps, operations, elements, components and / or combinations thereof supported by the present technical field. It should be understood that when we say that an element is "connected" or "coupled" to another element, the one element may be directly connected or coupled to the other element, or it may refer to that the one element and the other element establish a connection relationship through an intermediate element. In addition, the "connection" or "coupling" used herein may include wireless connection or wireless coupling. The term "and / or" used herein indicates at least one of the items defined by the term, for example, "A and / or B" indicates that it is implemented as "A", or is implemented as "A", or is implemented as "A and B".

[0038] In order to make the objectives, technical solutions and advantages of the present application clearer, the implementation methods of the present application will be further described in detail below with reference to the accompanying drawings.

[0039] The following describes several exemplary embodiments to illustrate the technical solutions of the embodiments of the present application and the technical effects produced by the technical solutions of the present application. It should be noted that the following embodiments can refer to, draw on or combine with each other, and the same terms, similar features and similar implementation steps in different embodiments will not be described repeatedly.

[0040] The large model-based broadcasting method, device, medium and product provided in this application are intended to solve at least one technical problem existing in the prior art.

[0041] A large model-based broadcasting method is provided in an embodiment of the present application. The device that executes the large model-based broadcasting method may be a mobile phone, a computer, a server, a cloud platform, and other terminals that can collect broadcast-related data and use the broadcast-related data to obtain broadcast information.

[0042] Alternatively, if Figure 1-Figure 3 As shown, the broadcast method based on the large model includes:

[0043] S101: Collect broadcast-related data corresponding to the area to be broadcasted.

[0044] Optionally, the area to be broadcasted may be an area where a device for playing broadcast information is located, or may be an area determined according to a received area selection instruction.

[0045] Optionally, before collecting the broadcast-related data corresponding to the area to be broadcasted, it can be detected whether the data collection conditions are currently met. If it is determined that the data collection conditions are met, the broadcast-related data is acquired. The data collection conditions may include at least one of the following: the current location is within a preset time collection range, the target object (such as a customer) appears in the area to be broadcasted, the number of target objects is greater than a preset number, and a data collection instruction is received.

[0046] Optionally, the broadcast-related data includes at least one of environmental data and behavioral data. The broadcast-related data can be collected by a data collection device set in the area to be broadcasted. Collecting the broadcast-related data corresponding to the area to be broadcasted includes: deploying a data collection device in the area to be broadcasted and acquiring social media data, the data collection device including at least one of a camera and a sensor; and collecting the broadcast-related data using the data collection device and social media data.

[0047] Optionally, environmental data and behavior data of the target object are collected through data collection equipment, and the target's emotional data and other behavior data that affect the behavior of the target object are obtained using social media data. Environmental data that can indicate the current environment of the area to be broadcast, such as temperature, crowding level, and gathering area, can also be obtained from social media data.

[0048] Optionally, the data acquisition device includes a camera, and the number of the cameras can be multiple. The data acquisition device is deployed in the area to be broadcast, including: installing the cameras at different positions in the area to be broadcast, and determining the monitoring areas of different cameras in the area to be broadcast according to the distance between the cameras.

[0049] Optionally, the installation location of the camera can be determined based on at least one of the structure, topography, power supply line settings of the area to be broadcasted, camera installation requirements, camera monitoring range, shooting angle and other information.

[0050] Optionally, after determining the installation location of the camera or installing the camera in the area to be broadcasted, the monitoring area can be divided by the shortest path algorithm and the distance between the cameras, and the camera corresponding to each monitoring area can be determined.

[0051] In one embodiment, the cameras are numbered a, b, c, and d, and the four cameras are set at different positions of the area to be broadcast to monitor different areas of the area to be broadcast. The shortest path between the cameras is calculated using the shortest path algorithm, and the monitoring range of the cameras is allocated based on the shortest path, thereby ensuring that each camera concentrates on monitoring the area it is responsible for and avoiding monitoring blind spots. Avoid multiple cameras from performing excessive repeated monitoring of the same area to save resources, improve monitoring efficiency, and enhance regional management. Specifically, if the shortest path algorithm is used to determine that the distance between cameras a and c is the shortest (shorter than the distance between a and c or d), the area covered by the monitoring range of a and c can be determined as monitoring area 1, and image data of monitoring area 1 can be obtained through a and c. Correspondingly, if the path between b and d is the shortest, the area covered by b and d is divided into monitoring area 2.

[0052] Optionally, after the monitoring area is divided, the monitoring of the monitoring area can be carried out in an independent monitoring or collaborative monitoring manner. Among them, when the independent monitoring method is adopted, an area can be divided for each camera according to the number of cameras in the monitoring area, and the camera performs monitoring operations on the divided area. After obtaining the monitoring data of the camera, the monitoring data is integrated into the monitoring data of the area to be broadcast, and the monitoring data is analyzed based on the monitoring data of the area to be broadcast to obtain broadcast-related data. When the collaborative monitoring method is adopted, the cameras corresponding to the monitoring area can work together, such as performing collaborative monitoring operations according to events occurring in the monitoring area or receiving instructions (such as determining that a suspicious person appears in the monitoring area, the cameras in the same monitoring area share the location information or movement trajectory of the suspicious person, so that each camera can quickly detect whether the suspicious person appears in its own detection range. If so, the image of the suspicious person is collected or the cameras share their own monitoring angle and monitoring range information so that each camera adjusts its own monitoring angle or monitoring range to reduce monitoring blind spots).

[0053] Optionally, when the data acquisition device is a camera, the broadcast-related data is collected using the data acquisition device, including: using the camera to obtain behavior data of the target object in the monitoring area, the behavior data including at least one of movement trajectory and entry and exit information.

[0054] Optionally, the target object may include a person, a vehicle, or other objects that appear in the area to be broadcasted. After the monitoring data of the area to be broadcasted is acquired by a camera, the target object is identified by the monitoring data, and an image of the target object is captured by the camera to acquire the behavior data of the target object.

[0055] Optionally, when the data acquisition device is a sensor, the sensor may include at least one of a fire detection sensor, a temperature sensor, a humidity sensor, a sound sensor, and an alarm. The sensor may be used to collect environmental data of the area to be broadcasted. The environmental data may include at least one of temperature, humidity, sound noise, an alarm, and a sensor working state.

[0056] Optionally, using social media data to collect broadcast-related data includes: extracting social media data, and extracting behavior data corresponding to the area to be broadcast in the social media data based on a preset filtering method, where the preset filtering method includes at least one of keyword filtering, user filtering, and time filtering.

[0057] In one embodiment, an application interface related to a social media application can be connected, and social media data can be extracted through the application interface, or social media data on the Internet can be collected through a browser. After obtaining the social media data, a corresponding filtering method is selected according to the type of the target object and the subject corresponding to the broadcast information. The social media data is filtered using the selected filtering method to obtain the behavior data corresponding to the area to be broadcast. Among them, when using the keyword filtering method, the required posts or comments can be extracted through keywords or topic tags related to the area to be broadcast. The keywords can be brands or places associated with the area to be broadcast. When filtering through the user filtering method, data can be filtered according to the user's geographic location, influence or other attributes. When using the time filtering method, data within a specific time period can be filtered based on the filtering requirements.

[0058] Specifically, when the area to be broadcasted is a shopping mall, the keywords may be keywords or topic tags related to the shopping mall, such as "shopping mall activities", "discount information", "service complaints", "brand recommendations", etc. Posts or comments containing these keywords are extracted.

[0059] Optionally, when using a preset filtering method to extract behavioral data, you can also first eliminate duplicate social media data, such as eliminating duplicate data with the same record content and the same or similar publishing time (within a few minutes or seconds). Among them, it is also possible to detect whether the texts of two social media data are the same or similar by comparing the text content. If they are the same or very similar, the texts of the two social media data can be marked as duplicate information to facilitate subsequent filtering operations. If the content of the two texts is the same, but the context is different, and the two are published in different conversations or at different times and for different objects, then the two texts can be retained and not marked as duplicate information.

[0060] Optionally, before obtaining behavioral data from social media data, preprocess the text of the social media data, such as deleting HTML tags, removing special characters, punctuation marks, and redundant spaces. Remove stop words (such as auxiliary words like "的" and "地"), and obtain the stem of the text. Duplicate removal (such as checking and deleting entries with similar or duplicate content) and denoising (such as advertisements unrelated to broadcast information, content automatically generated by the application providing social media data, etc.) can also be performed on the text during preprocessing.

[0061] S102: Extract broadcast features using broadcast association data and transmit the broadcast features to the large model.

[0062] Optionally, the broadcast features include at least one of entry and exit features, regional features, environmental features, and target object emotion features. The broadcast features are transmitted to the large model so that the large model generates broadcast information corresponding to the area to be broadcast based on the broadcast features.

[0063] Optionally, when the broadcast association data comes from a camera, extracting broadcast features using the broadcast association data includes: obtaining the playback area information corresponding to the broadcast device, and determining the regional features of the monitoring area based on the playback area information and the monitoring area; using behavioral data to determine the entry and exit features corresponding to the monitoring area.

[0064] Among them, the coverage range of the broadcast device in each monitoring area can be obtained, the area ratio of the coverage range relative to the corresponding monitoring area is detected, and the area ratio is determined as the regional feature of the monitoring area. The regional feature can be determined according to the coverage range that the broadcast can cover in the area to be broadcast and the area of the monitoring area, such as determining according to the area ratio of the monitoring area to the area to be broadcast.

[0065] In one embodiment, the divided monitoring areas include monitoring area 1 and monitoring area 2. The area ratio of monitoring area 1 to the area to be broadcast is obtained, and the area ratio is used as the regional feature of monitoring area 1. The regional feature can be represented in JSON format, such as: {Area 1: "Food Court (0.5)"}.

[0066] Optionally, when the area to be broadcast is a shopping mall, the entry and exit feature can be the pedestrian flow feature of the monitoring area. Correspondingly, the behavioral data is the pedestrian flow data of the monitoring area, and the pedestrian flow feature is obtained through the pedestrian flow data.

[0067] In one embodiment, the cameras in monitoring area 1 are divided into a, b, c, and d. Cameras a and c monitor the entry and exit of the pedestrian flow. Through the YOLO algorithm, analyze consecutive video frames over a period of time to track the movement trajectory of each person. Collect and store the pedestrian flow data, analyze the change in the pedestrian flow during a specific time period, and calculate the ratio of the number of people entering and leaving in monitoring area 1. The ratio is determined as the entry and exit feature.

[0068] Optionally, when the data acquisition device is a sensor, broadcast associated data is used to extract broadcast features, including: obtaining environmental data collected by the sensor, obtaining state change information from the environmental data using a preset algorithm, the preset algorithm including a vector machine algorithm; and determining environmental features based on the state change information and environmental data.

[0069] Optionally, the status change information includes information that affects the status of the area to be broadcast, such as fire, sensor failure, alarm, and environmental change trend.

[0070] In one embodiment, after obtaining environmental data, state change information is obtained according to the source of the environmental data and the vector machine algorithm. Specifically, if the environmental data is derived from one or more of a fire sensor, a temperature sensor, and a humidity sensor, the fire state information in the state change information can be obtained. If it is determined through environmental data that the sensor data is abnormal and the data conforms to the characteristic pattern of a fire, it is determined based on the vector machine algorithm that the current state is a fire state. Sensor failures can also be detected through a vector machine algorithm. For example, the sensor returns erroneous data or signals in the event of a failure. The erroneous data or signals are identified through a vector machine algorithm, and state change information of the sensor failure is given. Whether an alarm is triggered and the priority of the alarm after the alarm is triggered can also be obtained through the environmental data and the vector machine algorithm. For example, when high temperature is detected and the smoke concentration increases, it can be determined that an alarm is triggered and that the alarm is a high-priority emergency event.

[0071] Optionally, the environmental characteristics may be represented in the form of a feature vector, which includes state change information and sensor readings or statistics. For temperature, the temperature sensor reading may be used directly, and for humidity, the humidity sensor reading may be used. In addition, to facilitate understanding of whether there is danger, the feature vector may also include indication information of whether there is danger, such as using 1 to indicate the presence of danger and using 0 to indicate the absence of danger.

[0072] Optionally, the type of broadcast features extracted from the behavior data related to the social media data may be determined according to the purpose of the broadcast and the type of the area to be broadcasted.

[0073] Optionally, after obtaining the behavior data in the broadcast-related data through social media data, the broadcast-related data is used to extract broadcast features, including: extracting emotional text in the text corresponding to the behavior data, and obtaining emotional features of the target object based on the emotional text.

[0074] In one embodiment, the behavior data is stored in the form of a document, and the area to be broadcasted is a shopping mall. In order to improve the customer experience, the features extracted from the behavior data can be emotional features (such as the customer's emotional analysis results, the mentioned problems or needs, etc.). When extracting emotional features, the steps that can be taken include: using word frequency-inverse document frequency (TF-IDF) to calculate the importance of each word in the document, using NPL natural language processing to extract emotional text in the document and mark the emotional value corresponding to the emotional text (such as delicious (0.9), delicious (0.9), crowded (0.2), annoying (0.3), dangerous (0), lost (0.1), etc.). VADER (a rule-based emotional analysis tool) is used to extract emotional features from the marked emotional text to analyze and predict the emotional quality of subsequent user feedback data, for example: the food in the cake shop is good (0.7), a store in the clothing city is half price (0.88), and there is a beating in the cake shop (0.1).

[0075] Optionally, the large model may be a large language model (LIM) such as ChatGPTT, Gemini, Wenxinyiyan, Copilot, LLaMA, SAM, etc., which can perform text expansion or text generation according to input information.

[0076] Optionally, before transmitting the broadcast features to the large model, the acquired broadcast features may be filled into a preset prompt word template to generate prompt words, which are then input into the large model to obtain a more accurate output result.

[0077] S103: Acquire broadcast information corresponding to the broadcast features output by the large model, and perform broadcast operations based on the broadcast information.

[0078] In one embodiment, the large model may be ChatGPTT, and the broadcast features are sent to ChatGPTT in JSON format. ChatGPTT generates appropriate broadcast content by analyzing the broadcast features.

[0079] Optionally, the broadcast information may also include a priority of the broadcast information, and the priority may be determined based on the broadcast features received by the large model. After receiving the broadcast features, the large model analyzes the urgency or importance of the broadcast features, and determines which broadcast information needs to be broadcasted first based on the analysis results. For example, broadcast information related to fire alarms may be set to the highest priority, while general promotional information may have a lower priority.

[0080] Optionally, the broadcast information may further include a monitoring area corresponding to the broadcast information and a priority in the monitoring area.

[0081] In one embodiment, the monitoring area includes the food city area and the clothing city area. The broadcast information output by the large model is received, and the area corresponding to each broadcast information and the priority in the area are determined according to the priority in the broadcast information. For example, the food city area gives priority to broadcasting: "A conflict has occurred in the food city. Please stay calm, avoid related areas, and ensure your own safety. Thank you for your cooperation." The broadcast information played in the clothing city area is: "The clothing city currently has a large flow of people. Tourists with children should pay attention to the appropriate humidity but low temperature. Customers should pay attention to keeping warm. At the same time, the cake shop has launched new delicacies and welcomes everyone to come and taste them.

[0082] Optionally, after obtaining the broadcast information output by the large model, the broadcast information can also be output to the designated audit object. If the audit object receives the audit pass information, the broadcast operation is performed. If the audit object receives the abandonment instruction, the broadcast information is deleted. If the audit object receives the modification instruction, the broadcast information is modified according to the modification instruction, and the broadcast operation is performed according to the modified broadcast information.

[0083] Optionally, when there are multiple broadcasting devices, a broadcasting strategy may be determined according to the content of the broadcast information or the broadcast-related data, and the corresponding broadcasting devices may be controlled to work based on the broadcasting strategy. The broadcasting strategy may include at least one of the following: the broadcasting time, the broadcasting object, the broadcasting area, the volume, the number of plays, and the sound type. If the content of the broadcasting information is a fire, the broadcasting area is determined to be all areas, and the broadcasting devices in all areas are controlled to play the broadcasting information.

[0084] In one embodiment, Figure 2 As shown, the area to be broadcasted is a shopping mall. Environmental data (such as temperature and humidity) and customer behavior data (such as customer flow and dwell time) are collected in real time through sensors, and the peak time periods of customer activities and broadcast characteristics (such as environmental characteristics) of different areas of the shopping mall are extracted to provide basic data for the generation of broadcast information. The broadcast characteristics are output to ChatGPT, and ChatGPT is instructed to output the broadcast information, and the broadcast information output by ChatGPT based on the broadcast characteristics is obtained. According to the broadcast information, targeted broadcasts are carried out in the corresponding areas. For example, in areas with high passenger flow, the broadcast reminder is: "The current passenger flow in the fashion clothing area is large. It is recommended to go to other areas for shopping to avoid crowding." At the same time, the broadcast strategy can be adjusted according to the real-time data collected by sensors or cameras, and the volume of the broadcast equipment can be automatically increased in areas with high passenger flow.

[0085] The broadcasting method based on the big model of this application can automatically adjust the generated content according to different broadcasting environments (such as shopping malls, airports, conference centers, etc.) (adjusting the broadcasting content of different broadcasting areas according to the broadcasting information and collected data) to adapt to specific scenarios and needs. In addition, the method of generating broadcast information through the big model can be dynamically adjusted according to real-time data and user behavior, making the broadcast information closer to actual needs and environment. And it can adaptively generate content according to different broadcasting scenarios (such as shopping malls, airports, conference centers, etc.) to ensure the relevance and effectiveness of the information.

[0086] In an optional embodiment, an electronic device is provided, such as Figure 4 As shown, Figure 4 The electronic device 4000 shown includes: a processor 4001 and a memory 4003. The processor 4001 and the memory 4003 are connected, such as through a bus 4002. Optionally, the electronic device 4000 may also include a transceiver 4004, which may be used for data interaction between the electronic device and other electronic devices, such as data transmission and / or data reception. It should be noted that in actual applications, the transceiver 4004 is not limited to one, and the structure of the electronic device 4000 does not constitute a limitation on the embodiments of the present application.

[0087] Processor 4001 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It may implement or execute various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. Processor 4001 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, and the like.

[0088] The bus 4002 may include a path to transmit information between the above components. The bus 4002 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus 4002 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, only one thick line is used in the figure, but it does not mean that there is only one bus or one type of bus.

[0089] Memory 4003 can be ROM (Read Only Memory) or other types of static storage devices that can store static information and instructions, RAM (Random Access Memory) or other types of dynamic storage devices that can store information and instructions, or it can be EEPROM (Electrically Erasable Programmable Read Only Memory), CD-ROM (Compact Disc Read Only Memory) or other optical disk storage, optical disk storage (including compressed optical disk, laser disc, optical disk, digital versatile disc, Blu-ray disc, etc.), magnetic disk storage medium, other magnetic storage devices or any other medium that can be used to carry or store computer programs and can be read by a computer, without limitation here.

[0090] The memory 4003 is used to store the computer program for executing the embodiment of the present application, and the execution is controlled by the processor 4001. The processor 4001 is used to execute the computer program stored in the memory 4003 to implement the steps shown in the above method embodiment.

[0091] Among them, the electronic device can be any electronic product that can interact with an object, such as a personal computer, a tablet computer, a smart phone, a personal digital assistant (PDA), a game console, an interactive network television (IPTV), a smart wearable device, etc.

[0092] The electronic device may also include a network device and / or an object device, wherein the network device includes, but is not limited to, a single network server, a server group consisting of multiple network servers, or a cloud consisting of a large number of hosts or network servers for cloud computing.

[0093] The network where the electronic device is located includes but is not limited to the Internet, a wide area network, a metropolitan area network, a local area network, a virtual private network (Virtual Private Network, VPN), etc.

[0094] An embodiment of the present application provides a computer-readable storage medium, which includes a computer program. When the computer program is executed by a processor, the steps and corresponding contents of the aforementioned method embodiment can be implemented.

[0095] An embodiment of the present application provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the steps and corresponding contents of the aforementioned method embodiment can be implemented.

[0096] The terms "first", "second", "third", "fourth", "1", "2", etc. (if any) in the specification and claims of this application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than that shown or described in the drawings.

[0097] It should be understood that, although each operation step is indicated by arrows in the flowchart of the embodiment of the present application, the implementation order of these steps is not limited to the order indicated by the arrows. Unless clearly stated herein, in some implementation scenarios of the embodiment of the present application, the implementation steps in each flowchart can be performed in other orders according to demand. In addition, some or all of the steps in each flowchart may include multiple sub-steps or multiple stages based on actual implementation scenarios. Some or all of these sub-steps or stages may be executed at the same time, and each sub-step or stage in these sub-steps or stages may also be executed at different times respectively. In different scenarios of execution time, the execution order of these sub-steps or stages may be flexibly configured according to demand, and the embodiment of the present application does not limit this.

[0098] The above is only an optional implementation method for some implementation scenarios of the present application. It should be pointed out that for ordinary technicians in this technical field, without departing from the technical concept of the solution of the present application, other similar implementation methods based on the technical ideas of the present application are also within the protection scope of the embodiments of the present application.

Claims

1. A broadcasting method based on a large model, characterized in that: The method comprises: Collecting broadcast-related data corresponding to the area to be broadcasted, wherein the broadcast-related data includes at least one of environmental data and behavioral data; Extracting broadcast features using the broadcast-related data, and transmitting the broadcast features to the big model, wherein the broadcast features include at least one of entry and exit features, regional features, environmental features, and target object emotion features; The broadcast information corresponding to the broadcast feature output by the large model is obtained, and a broadcast operation is performed based on the broadcast information.

2. The broadcasting method based on a large model according to claim 1, characterized in that: The collecting of broadcast-related data corresponding to the area to be broadcasted includes: Deploy a data collection device in the area to be broadcasted and obtain social media data, wherein the data collection device includes at least one of a camera and a sensor; The broadcast associated data is collected using the data collection device and the social media data.

3. The broadcasting method based on a large model according to claim 2, characterized in that: The data acquisition device includes a camera, and the step of deploying the data acquisition device in the area to be broadcast includes: Installing the cameras at different positions of the area to be broadcasted, and determining monitoring areas of different cameras in the area to be broadcasted according to the distances between the cameras; Collecting the broadcast-related data using the data collection device includes: The camera is used to obtain behavior data of the target object in the monitoring area, and the behavior data includes at least one of a movement trajectory and entry and exit information.

4. The broadcasting method based on a large model according to claim 3, characterized in that: The extracting broadcast features by using the broadcast associated data includes: Acquire coverage information corresponding to the broadcasting device, and determine the regional characteristics of the monitoring area according to the coverage information and the monitoring area; The behavior data is used to determine the entry and exit characteristics corresponding to the monitoring area.

5. The broadcasting method based on a large model according to claim 2, characterized in that: The data collection device includes a sensor, and the extracting broadcast features by using the broadcast-related data includes: Acquire environmental data collected by the sensor, and obtain state change information from the environmental data using a preset algorithm, wherein the preset algorithm includes a vector machine algorithm; The environmental characteristics are determined according to the state change information and the environmental data.

6. The broadcasting method based on a large model according to claim 2, characterized in that: Collecting the broadcast-related data using the social media data includes: The social media data is extracted, and the behavior data corresponding to the to-be-broadcast area in the social media data is extracted based on a preset filtering method, wherein the preset filtering method includes at least one of keyword filtering, user filtering, and time filtering.

7. The broadcasting method based on a large model according to claim 6, characterized in that: The extracting broadcast features by using the broadcast associated data includes: The emotional text in the text corresponding to the behavior data is extracted, and the emotional characteristics of the target object are obtained based on the emotional text.

8. An electronic device comprising a memory, a processor and a computer program stored in the memory, characterized in that: The processor executes the computer program to implement the steps of the method according to any one of claims 1 to 7.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images