Intelligent service method and system

Abstract

The application relates to the technical field of intelligent service platforms, and particularly discloses an intelligent service method and system, which comprises the following steps: acquiring real-time personnel information of each service unit based on an information collector installed in a public area, and constructing a crowd portrait of the service unit; determining a service demand table according to the crowd portrait; the service demand table comprises a service type and a service quota; real-time receiving of a service request sent by the service unit, generation of a service instruction, analysis of the service request, and updating of a generation process of the service demand table; and pre-scheduling of service resources according to service demand tables of all service units. According to the application, the demand of a customer can be predicted based on available public customer information, and service resources can be prepared in advance according to the prediction result. Compared with a traditional scheme, the preparation process is advanced, although the human cost is increased, but from the perspective of the customer, the service efficiency is greatly improved.

Description

Technical Field

[0001] This invention relates to the field of intelligent service platform technology, specifically an intelligent service method and system. Background Technology

[0002] Intelligent services refer to the use of technologies such as artificial intelligence (AI), big data, the Internet of Things (IoT), and cloud computing to improve the automation, personalization, and intelligence of services, thereby meeting the diverse needs of users and improving user experience and service efficiency.

[0003] Intelligent services are widely used in the service industry. For example, hotels, KTVs, and restaurants are equipped with intelligent systems to receive customer requests remotely and provide services quickly. However, existing service architectures do not have lead time; services can only be provided after a customer sends a request, which results in a certain delay. How to improve service efficiency is the technical problem that this invention aims to solve. Summary of the Invention

[0004] The purpose of this invention is to provide an intelligent service method and system to solve the problems mentioned in the background art.

[0005] To achieve the above objectives, the present invention provides the following technical solution:

[0006] An intelligent service method, the method comprising:

[0007] Real-time personnel information of each service unit is obtained by information collectors installed in public areas, and a population profile of the service unit is constructed.

[0008] A service demand table is determined based on the aforementioned user profile; the service demand table includes service types and service limits.

[0009] The process of receiving service requests from service units in real time, generating service instructions, analyzing the service requests, and updating the service requirement table is also performed.

[0010] Service resources are pre-scheduled periodically based on the service demand tables of all service units;

[0011] The crowd profile is a collection of person profiles, and each person profile is a numerical group that corresponds one-to-one with a person. Each element in the numerical group corresponds to a preset feature.

[0012] Furthermore, the step of constructing a crowd profile for each service unit by acquiring real-time personnel information from information collectors installed in public areas includes:

[0013] For any service unit, the usage information of that service unit is obtained through the information entry port; the usage information includes the number of users and the usage period.

[0014] The system uses cameras installed in public areas to capture the personal characteristics of people entering and exiting the service unit.

[0015] Based on the entry and exit statistics of each person's characteristics, the service unit obtains a population profile by analyzing the characteristics of people during the usage period.

[0016] Furthermore, the step of acquiring the personnel characteristics of people entering and exiting the service unit based on cameras installed in public areas includes:

[0017] People are tracked and their locations are determined by cameras installed in public areas;

[0018] Contour recognition is performed on the personnel area, and the upper garment area and lower garment area are determined based on the relative position of each contour in the personnel area;

[0019] The upper garment area and the lower garment area are identified, and the mode price range of the identification results is queried. The mode price range is then used as a personnel feature.

[0020] The term "mode price range" refers to the mode of the price ranges corresponding to all identification results.

[0021] Furthermore, the step of determining the service demand table based on the user profile includes:

[0022] Read all the mode price ranges in the audience profile;

[0023] Determine the consumer characteristics of the population based on the aforementioned mode price range;

[0024] Input the consumption characteristics of the population into the trained neural network model to obtain the service type and service amount, and construct a service demand table;

[0025] The training process of the neural network model is as follows:

[0026] Select service units within a preset time and space range to obtain their user profiles and actual consumption records;

[0027] Read all the mode price ranges in the audience profile, and determine the audience consumption characteristics based on the mode price ranges;

[0028] Establish a sample set of population consumption characteristics and actual consumption records; the actual consumption records include service type and service amount;

[0029] Training a neural network model based on a sample set;

[0030] The process of determining the consumption characteristics of the population is as follows:

[0031]

[0032] In the formula, S represents the consumption characteristics of the population, N represents the total number of people in the population profile, and Z represents the total number of people in the population profile. i Let α represent the i-th eigenvalue. i The coefficient corresponding to the i-th eigenvalue is represented by β; β is a preset correction coefficient; S∈{A1,A2,…,A2} N},|S|=k represents the set {A1,A2,…,A}. N} Randomly select a subset consisting of k mode value intervals, ∩ i∈S (A j A represents the intersection of the mode value intervals in set S. j Represents the i-th mode price interval in S; j∈[1,k], k∈[1,N]; E{∩ i∈S (A j S∈{A1,A2,…,A N},|S|=k} represents finding the mean of the midpoint values ​​of the intersection.

[0033] Furthermore, the steps of the real-time receiving service unit sending service requests, generating service instructions, and simultaneously analyzing the service requests to update the service requirement table include:

[0034] The system receives service types and service limits from service units in real time, uploads the service units, their service types, and service limits to the central control terminal, and generates service instructions.

[0035] The service type and service amount of the statistical service unit are used as real consumption records to update the sample set.

[0036] Furthermore, the step of pre-scheduling service resources based on the service demand table of all service units includes:

[0037] Every preset period, retrieve the service requirement table of all service units in the previous period;

[0038] The service units are combined according to their positional relationships, and the corresponding service demand tables are merged.

[0039] Service resources are pre-scheduled based on the merged service demand table.

[0040] The present invention also provides an intelligent service system, the system comprising:

[0041] The crowd profiling module is used to construct crowd profiles for each service unit based on real-time personnel information obtained from information collectors installed in public areas.

[0042] The service demand determination module is used to determine a service demand table based on the user profile; the service demand table includes service type and service amount.

[0043] The service instruction generation module is used to receive service requests sent by service units in real time, generate service instructions, analyze the service requests, and update the service requirement table generation process.

[0044] The resource pre-scheduling module is used to pre-schedule service resources periodically based on the service demand table of all service units;

[0045] The crowd profile is a collection of person profiles, and each person profile is a numerical group that corresponds one-to-one with a person. Each element in the numerical group corresponds to a preset feature.

[0046] Furthermore, the crowd profiling module includes:

[0047] The information query unit is used to retrieve the usage information of any service unit based on the information input port; the usage information includes the number of users and the usage period.

[0048] The personnel feature detection unit is used to obtain the personnel features of people entering and exiting the service unit based on cameras installed in public areas;

[0049] The personnel characteristic statistics unit is used to statistically analyze the personnel characteristics of the service unit during the usage period based on the entry and exit status corresponding to each personnel characteristic, and to obtain a crowd profile as the crowd profile.

[0050] Furthermore, the personnel feature detection unit includes:

[0051] The personnel tracking subunit is used to track personnel and locate their positions based on cameras installed in public areas.

[0052] The contour recognition subunit is used to perform contour recognition on the personnel area and determine the upper garment area and lower garment area based on the relative position of each contour in the personnel area.

[0053] The object recognition subunit is used to recognize objects in the upper garment area and the lower garment area, query the mode price range of the object recognition results, and use the mode price range as a personnel feature.

[0054] The term "mode price range" refers to the mode of the price ranges corresponding to all identification results.

[0055] Furthermore, the service requirement determination module includes:

[0056] The price range reading unit is used to read all the mode price ranges in the audience profile;

[0057] A consumption characteristic determination unit is used to determine the consumption characteristics of the population based on the mode price range;

[0058] Construct an execution unit to input the consumption characteristics of the population into the trained neural network model, obtain the service type and service amount, and construct a service demand table;

[0059] The training process of the neural network model is as follows:

[0060] Select service units within a preset time and space range to obtain their user profiles and actual consumption records;

[0061] Read all the mode price ranges in the audience profile, and determine the audience consumption characteristics based on the mode price ranges;

[0062] Establish a sample set of population consumption characteristics and actual consumption records; the actual consumption records include service type and service amount;

[0063] Training a neural network model based on a sample set;

[0064] The process of determining the consumption characteristics of the population is as follows:

[0065]

[0066] In the formula, S represents the consumption characteristics of the population, N represents the total number of people in the population profile, and Z represents the total number of people in the population profile. i Let α represent the i-th eigenvalue. i The coefficient corresponding to the i-th eigenvalue is represented by β; β is a preset correction coefficient; S∈{A1,A2,…,A2} N},|S|=k represents the set {A1,A2,…,A}. N} Randomly select a subset consisting of k mode value intervals, ∩ i∈S (A j A represents the intersection of the mode value intervals in set S. j Represents the i-th mode price interval in S; j∈[1,k], k∈[1,N]; E{∩ i∈S (A j S∈{A1,A2,…,A N},|S|=k} represents finding the mean of the midpoint values ​​of the intersection.

[0067] Compared with the prior art, the beneficial effects of the present invention are: the present invention predicts the demand of customers based on publicly available customer information and prepares service resources in advance based on the prediction results. Compared with the traditional solution, the preparation process is brought forward. Although it increases labor costs, it greatly improves service efficiency from the customer's perspective. Attached Figure Description

[0068] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention.

[0069] Figure 1 A flowchart for intelligent service methods.

[0070] Figure 2 The first sub-process flowchart for the intelligent service method.

[0071] Figure 3 This is the second sub-process flowchart for the intelligent service method.

[0072] Figure 4 This is the third sub-process flowchart for the intelligent service method.

[0073] Figure 5 This is the fourth sub-process flowchart for the intelligent service method.

[0074] Figure 6 This is a structural diagram of the intelligent service system. Detailed Implementation

[0075] To make the technical problems to be solved, the technical solutions, and the beneficial effects of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present invention and are not intended to limit the present invention.

[0076] Figure 1 The flowchart of the intelligent service method is shown in this embodiment of the invention. The method includes:

[0077] Step S100: Based on the information collectors installed in public areas, obtain real-time personnel information of each service unit and construct a population profile of the service unit;

[0078] The technical solution of this invention is applied to private entertainment service venues, such as restaurants, hotels, and KTVs, which contain private rooms. Information inside the private rooms is not accessible as they are considered private areas for customers. Areas such as corridors, lobbies, and reception areas are called public areas. Information collection devices are installed in these public areas for security management of the entire venue. These information collection devices are also considered infrastructure in existing venues. The information collection devices include information input devices installed at the reception desk and cameras that cover the entire public area.

[0079] It should be noted that the information collectors in public areas have the authority to collect information about the public area, not personal information. Of course, the administrators of the information collectors cannot arbitrarily disseminate the information they collect, as there are relevant regulations. In the technical solution of this invention, in order to clarify the issue of permissions, the location of the information collectors needs to be clearly informed to the user. When the user still chooses to use the public space, it is considered that he has clearly granted the permission to collect information, rather than the permission to disseminate information.

[0080] The smallest unit of service is called a service unit. For a hotel, this means each room; for a restaurant, it means each private room; and for a KTV, it means each private room. By collecting public information through information collectors, we can obtain the number of people in each service unit and the characteristics of each person, which is called a crowd profile.

[0081] It must be noted that the above content must be based on known and available data, such as the number of consumers (some of which involve specific identity information, such as hotels, and these are all information that complies with regulations) and information on the movement of people in public areas. This information must be data that both parties agree to be available, and information that customers refuse to have accessed cannot be obtained.

[0082] Step S200: Determine a service demand table based on the described user profile; the service demand table includes service types and service limits;

[0083] The obtained crowd profile is used to reflect the demand characteristics of the people in the private room. By identifying the crowd profile, a service demand table can be determined. The service demand table includes service type and service amount. The service type is used to represent which service is provided, and the service amount is a higher probability that represents how much service the user needs. For example, drinking water demand is a service type, and water consumption is the corresponding service amount. Since different service types have different numerical units, they are collectively referred to as service amount.

[0084] Specifically, the mapping relationship between user profiles and service needs can be obtained by training a neural network model, or a table can be created based on historical data, and the user profile can be queried in the table when needed.

[0085] It's worth mentioning that the simplest way to create a user profile is by using a set of ages, that is, the set of ages of all personnel in the service unit. This is a numerical group. On this basis, a gender parameter can also be introduced. Both gender and age parameters affect service demand. By statistically analyzing different combinations of gender and age and recording the corresponding historical demand, a record table can be obtained. When someone in the service unit uses the service, the gender and age of the person are obtained, and the closest historical demand is searched in the record table, which can then be used as the service demand table.

[0086] In summary, the population profile is a collection of person profiles, and each person profile is a numerical group that corresponds one-to-one with a person. Each element in the numerical group corresponds to a preset feature.

[0087] Step S300: Receive service requests sent by the service unit in real time, generate service instructions, analyze the service requests, and update the service requirement table generation process.

[0088] Step S300 is the actual application process: receiving a service request sent by any service unit, generating a service instruction, providing the service, and at the same time recording the provided services to obtain historical requirements; historical requirements are used to update the service requirement table generation process; in the above scheme, this means updating the record table.

[0089] Step S400: Periodically pre-schedule service resources based on the service demand table of all service units;

[0090] Service resources are pre-scheduled at preset intervals, such as one hour, which can greatly improve service speed (reducing resource preparation time). It should be noted that since customers are constantly changing, the customer profile of each service unit changes over time, and the corresponding service demand table also changes over time. Therefore, the service demand table of all service units is different at preset intervals. Thus, the pre-scheduling scheme for service resources is not static, and the pre-scheduling scheme is different at different times.

[0091] Specifically, the pre-scheduling process involves preparing service resources in advance based on the predicted demand (predicted demand table) for each service unit. The accuracy of the predicted demand is relatively high, but not 100%. Therefore, some pre-planning work may not be implemented, which increases labor costs to some extent. However, from the customer's perspective, the service efficiency is extremely high, and the service quality is high.

[0092] Figure 2The first sub-process flowchart of the intelligent service method includes the step of constructing a crowd profile for each service unit by acquiring real-time personnel information from information collectors installed in public areas:

[0093] Step S101: For any service unit, obtain the usage information of the service unit through the information input port; the usage information includes the number of users and the usage time period;

[0094] Step S102: Obtain the personnel characteristics of people entering and exiting the service unit based on the cameras installed in the public area;

[0095] Step S103: Based on the entry and exit data corresponding to each person's characteristics, the service unit statistically analyzes the personnel characteristics during the usage period to obtain a crowd profile.

[0096] In one example of the technical solution of the present invention, the process of constructing a crowd profile is described in detail. For any service unit, the usage information of the service unit is obtained through the information input port. The usage information is the number of people using it and the time period, referred to as the number of users and the usage period. The information input port is built into the central control terminal, which is generally placed on the computer at the front desk in the service location.

[0097] By capturing real-time video from cameras installed in public areas and identifying the video data, it is possible to obtain the characteristics of people entering and exiting each service unit. This allows us to calculate who is inside the service unit during the usage period and statistically analyze their characteristics, creating a crowd profile.

[0098] Among them, the video recognition solution can quickly determine whether a person is entering or leaving the service unit by using existing target tracking algorithms.

[0099] Specifically, the step of acquiring the personnel characteristics of people entering and exiting the service unit based on cameras installed in public areas includes:

[0100] People are tracked and their locations are determined by cameras installed in public areas;

[0101] Contour recognition is performed on the personnel area, and the upper garment area and lower garment area are determined based on the relative position of each contour in the personnel area;

[0102] The upper garment area and the lower garment area are identified, and the mode price range of the identification results is queried. The mode price range is then used as a personnel feature.

[0103] The term "mode price range" refers to the mode of the price ranges corresponding to all identification results.

[0104] In one example of the technical solution of this invention, by using a camera installed in a public area to track people, the area of ​​people can be located. By performing contour recognition on the area of ​​people, the upper garment area and the lower garment area can be further located. By performing object recognition on the upper garment area and the lower garment area, a variety of object recognition results can be obtained. For the object recognition results of clothing, a price is often attached. There are many recognition results and many prices. The prices are classified into intervals to simplify the types of prices. The price interval corresponding to the most recognition results is obtained, which is called the mode price interval, and can be used as a feature of people.

[0105] The above solution actually provides personnel characteristics other than age and gender. It relies on existing object recognition technology to obtain the average price of the user's clothing and predict their spending power. In most cases, clothing prices are positively correlated with consumption level (service demand). This invention does not require accuracy, as long as the condition of positive correlation is met.

[0106] Figure 3 The second sub-process flowchart of the intelligent service method includes the step of determining the service demand table based on the user profile:

[0107] Step S201: Read all the mode price ranges in the audience profile;

[0108] Step S202: Determine the consumption characteristics of the population based on the mode price range;

[0109] Step S203: Input the consumption characteristics of the population into the trained neural network model to obtain the service type and service amount, and construct a service demand table;

[0110] The above content defines the application process of audience profiling. In this process, the characteristics of the people in the audience profile are limited to the mode price range. By analyzing all the mode price ranges in the audience profile, the consumption characteristics of the audience are extracted. The consumption characteristics of the audience are the comprehensive values ​​determined by the mode price ranges of multiple people. These values ​​are then input into a trained neural network model, and the resulting service types and service amounts can be used to construct a service demand table.

[0111] The training process of the neural network model is as follows:

[0112] Select service units within a preset time and space range to obtain their user profiles and actual consumption records;

[0113] Read all the mode price ranges in the audience profile, and determine the audience consumption characteristics based on the mode price ranges;

[0114] Establish a sample set of population consumption characteristics and actual consumption records; the actual consumption records include service type and service amount;

[0115] Training a neural network model based on a sample set;

[0116] The above describes the training process of the neural network model. The key to the training process lies in the sample construction process. First, the management sets a spatiotemporal range, which represents the time and space ranges. The time range indicates the service units within a specific time period, and the space range indicates the service units in specific locations. Service units are selected within the preset spatiotemporal range, and their customer profiles and actual consumption records are obtained (both are known data in this invention). All the mode price ranges in the customer profiles are read, and the customer consumption characteristics are determined based on these ranges. The customer consumption characteristics are used as input, and the actual consumption records are used as output to construct a sample set. The neural network model is then trained based on this sample set. The actual consumption records include service type and service amount.

[0117] In the technical solution of this invention, there is a conversion relationship between the mode price range and the consumption characteristics of the population. One feasible solution is as follows:

[0118] The process of determining the consumption characteristics of a population is as follows:

[0119]

[0120] In the formula, S represents the consumption characteristics of the population, N represents the total number of people in the population profile, and Z represents the total number of people in the population profile. i Let α represent the i-th eigenvalue. i The coefficient corresponding to the i-th eigenvalue is represented by β; β is a preset correction coefficient; S∈{A1,A2,…,A2} N},|S|=k represents the set {A1,A2,…,A}. N} Randomly select a subset consisting of k mode value intervals, ∩ i∈s (A j A represents the intersection of the mode value intervals in set S. j Represents the i-th mode price interval in S; j∈[1,k], k∈[1,N]; E{∩ i∈S (A j S∈{A1,A2,…,A N},|S|=k} represents finding the mean of the midpoint values ​​of the intersection.

[0121] The above provides a specific scheme for determining the consumption characteristics of a population. First, query the mode price range for all individuals. Then, select quantities sequentially. For example, if there are 10 individuals, the quantities are integers from 1 to 10. Select the mode price range based on the quantity, and calculate the intersection and select the midpoint value of the intersection. Since the selected individuals may be different, for example, selecting 9 individuals out of 10, there are 10 ways to select them, resulting in 9 intersection results and 9 midpoint values. Calculate the mean of the 9 midpoint values ​​and use it as the feature value for the quantity 9. Finally, calculate the mean of all feature values ​​to obtain a single value, which is used as the consumption characteristic of the population.

[0122] Figure 4 The third sub-flowchart of the intelligent service method includes the following steps in the process of generating a service request, generating a service instruction, analyzing the service request, and updating the service requirement table:

[0123] Step S301: Receive the service type and service limit sent by the service unit in real time, upload the service unit, its service type, and service limit to the central control terminal, and generate service instructions;

[0124] Step S302: Statistically analyze the service type and service amount of the service unit as actual consumption records, and update the sample set.

[0125] In practical applications, upon receiving the service type and service amount sent by the service unit, staff must be immediately arranged to provide the service, that is, to provide service resources. The service type indicates which type of service the customer in the service unit needs, and the service amount indicates how much is needed. At the same time, the service types and service amounts sent by all service units are counted to generate historical records, called real consumption records. At this time, the number of recent samples in the sample set increases. The more recent samples there are, the smaller the loss function of the neural network model and the higher the accuracy.

[0126] Figure 5 The fourth sub-process flowchart of the intelligent service method includes the step of pre-scheduling service resources based on the service demand table of all service units, which includes:

[0127] Step S401: Every preset period, obtain the service demand table of all service units in the previous period;

[0128] Step S402: Combine the service units according to their positional relationships, and merge the corresponding service demand tables.

[0129] Step S403: Pre-schedule service resources according to the merged service demand table.

[0130] Steps S401 to S403 are the key points of the technical solution of this invention. Every certain period of time (a preset cycle) a pre-scheduling process is executed. Starting from the current time, a cycle range is reversed to obtain the service demand tables of all service units in the previous cycle. These service demand tables are predicted service demand tables (the actual demand will be provided as soon as it is received in step S300). According to the positional relationship of the service units, similar service units are grouped into one category, and their corresponding service demand tables are merged. This process is equivalent to partitioning. Finally, service resources are prepared in advance according to the service demand table of each zone. This is the meaning of pre-scheduling.

[0131] Figure 6 This is a structural block diagram of an intelligent service system. In this embodiment of the invention, an intelligent service system 10 includes:

[0132] The crowd profiling module 11 is used to construct crowd profiles for each service unit based on real-time personnel information obtained from information collectors installed in public areas.

[0133] The service demand determination module 12 is used to determine a service demand table based on the user profile; the service demand table includes service type and service amount.

[0134] The service instruction generation module 13 is used to receive service requests sent by the service unit in real time, generate service instructions, analyze the service requests, and update the service requirement table generation process.

[0135] Resource pre-scheduling module 14 is used to pre-schedule service resources periodically based on the service demand table of all service units;

[0136] The crowd profile is a collection of person profiles, and each person profile is a numerical group that corresponds one-to-one with a person. Each element in the numerical group corresponds to a preset feature.

[0137] Furthermore, the crowd profiling module 11 includes:

[0138] The information query unit is used to retrieve the usage information of any service unit based on the information input port; the usage information includes the number of users and the usage period.

[0139] The personnel feature detection unit is used to obtain the personnel features of people entering and exiting the service unit based on cameras installed in public areas;

[0140] The personnel characteristic statistics unit is used to statistically analyze the personnel characteristics of the service unit during the usage period based on the entry and exit status corresponding to each personnel characteristic, and to obtain a crowd profile as the crowd profile.

[0141] Specifically, the personnel feature detection unit includes:

[0142] The personnel tracking subunit is used to track personnel and locate their positions based on cameras installed in public areas.

[0143] The contour recognition subunit is used to perform contour recognition on the personnel area and determine the upper garment area and lower garment area based on the relative position of each contour in the personnel area.

[0144] The object recognition subunit is used to recognize objects in the upper garment area and the lower garment area, query the mode price range of the object recognition results, and use the mode price range as a personnel feature.

[0145] The term "mode price range" refers to the mode of the price ranges corresponding to all identification results.

[0146] Furthermore, the service demand determination module 12 includes:

[0147] The price range reading unit is used to read all the mode price ranges in the audience profile;

[0148] A consumption characteristic determination unit is used to determine the consumption characteristics of the population based on the mode price range;

[0149] Construct an execution unit to input the consumption characteristics of the population into the trained neural network model, obtain the service type and service amount, and construct a service demand table;

[0150] The training process of the neural network model is as follows:

[0151] Select service units within a preset time and space range to obtain their user profiles and actual consumption records;

[0152] Read all the mode price ranges in the audience profile, and determine the audience consumption characteristics based on the mode price ranges;

[0153] Establish a sample set of population consumption characteristics and actual consumption records; the actual consumption records include service type and service amount;

[0154] Training a neural network model based on a sample set;

[0155] The process of determining the consumption characteristics of the population is as follows:

[0156]

[0157] In the formula, S represents the consumption characteristics of the population, N represents the total number of people in the population profile, and Z represents the total number of people in the population profile. i Let α represent the i-th eigenvalue. iThe coefficient corresponding to the i-th eigenvalue is represented by β; β is a preset correction coefficient; S∈{A1,A2,…,A2} N},|S|=k represents the set {A1,A2,…,A}. N} Randomly select a subset consisting of k mode value intervals, ∩ i∈S (A j A represents the intersection of the mode value intervals in set S. j Represents the i-th mode price interval in S; j∈[1,k], k∈[1,N]; E{∩ i∈S (A j S∈{A1,A2,…,A N},|S|=k} represents finding the mean of the midpoint values ​​of the intersection.

[0158] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. An intelligent service method, characterized in that, The method includes: Real-time personnel information of each service unit is obtained by information collectors installed in public areas, and a population profile of the service unit is constructed. A service demand table is determined based on the aforementioned user profile; the service demand table includes service types and service limits. The process of receiving service requests from service units in real time, generating service instructions, analyzing the service requests, and updating the service requirement table is also performed. Service resources are pre-scheduled periodically based on the service demand tables of all service units; The crowd profile is a collection of person profiles, and each person profile is a numerical group that corresponds one-to-one with a person. Each element in the numerical group corresponds to a preset feature. The step of determining the service demand table based on the user profile includes: Read all the mode price ranges in the audience profile; Determine the consumer characteristics of the population based on the aforementioned mode price range; Input the consumption characteristics of the population into the trained neural network model to obtain the service type and service amount, and construct a service demand table; The training process of the neural network model is as follows: Select service units within a preset time and space range to obtain their user profiles and actual consumption records; Read all the mode price ranges in the audience profile, and determine the audience consumption characteristics based on the mode price ranges; Establish a sample set of population consumption characteristics and actual consumption records; the actual consumption records include service type and service amount; Training a neural network model based on a sample set; The process of determining the consumption characteristics of the population is as follows: ； ； ； In the formula, Indicates the consumption characteristics of the population. This represents the total number of people in the crowd profile. Indicates the first 1 eigenvalue, Indicates the first The coefficients corresponding to each eigenvalue; This is the preset correction factor; Indicates from set Choose any A subset consisting of the value intervals of the mode. Represents a set The intersection of the various mode value intervals in the middle. express The first in The price range of the mode; , ; This represents finding the mean of the midpoint values ​​of the intersection.

2. The intelligent service method according to claim 1, characterized in that, The steps for constructing a crowd profile for each service unit by acquiring real-time personnel information from information collectors installed in public areas include: For any service unit, the usage information of that service unit is obtained through the information entry port; the usage information includes the number of users and the usage period. The system uses cameras installed in public areas to capture the personal characteristics of people entering and exiting the service unit. Based on the entry and exit statistics of each person's characteristics, the service unit obtains a population profile by analyzing the characteristics of people during the usage period.

3. The intelligent service method according to claim 2, characterized in that, The step of obtaining the personnel characteristics of people entering and exiting the service unit based on cameras installed in public areas includes: People are tracked and their locations are determined by cameras installed in public areas; Contour recognition is performed on the personnel area, and the upper garment area and lower garment area are determined based on the relative position of each contour in the personnel area; The upper garment area and the lower garment area are identified, and the mode price range of the identification results is queried. The mode price range is then used as a personnel feature. The term "mode price range" refers to the mode of the price ranges corresponding to all identification results.

4. The intelligent service method according to claim 1, characterized in that, The steps of the real-time receiving service unit sending service requests, generating service instructions, analyzing the service requests, and updating the service request table include: The system receives service types and service limits from service units in real time, uploads the service units, their service types, and service limits to the central control terminal, and generates service instructions. The service type and service amount of the statistical service unit are used as real consumption records to update the sample set.

5. The intelligent service method according to claim 1, characterized in that, The step of pre-scheduling service resources based on the service demand table of all service units includes: Every preset period, retrieve the service requirement table of all service units in the previous period; The service units are combined according to their positional relationships, and the corresponding service demand tables are merged. Service resources are pre-scheduled based on the merged service demand table.

6. An intelligent service system, characterized in that, The system includes: The crowd profiling module is used to construct crowd profiles for each service unit based on real-time personnel information obtained from information collectors installed in public areas. The service demand determination module is used to determine a service demand table based on the user profile; the service demand table includes service type and service amount. The service instruction generation module is used to receive service requests sent by service units in real time, generate service instructions, analyze the service requests, and update the service requirement table generation process. The resource pre-scheduling module is used to pre-schedule service resources periodically based on the service demand table of all service units; The crowd profile is a collection of person profiles, and each person profile is a numerical group that corresponds one-to-one with a person. Each element in the numerical group corresponds to a preset feature. The service requirement determination module includes: The price range reading unit is used to read all the mode price ranges in the audience profile; A consumption characteristic determination unit is used to determine the consumption characteristics of the population based on the mode price range; Construct an execution unit to input the consumption characteristics of the population into the trained neural network model, obtain the service type and service amount, and construct a service demand table; The training process of the neural network model is as follows: Select service units within a preset time and space range to obtain their user profiles and actual consumption records; Read all the mode price ranges in the audience profile, and determine the audience consumption characteristics based on the mode price ranges; Establish a sample set of population consumption characteristics and actual consumption records; the actual consumption records include service type and service amount; Training a neural network model based on a sample set; The process of determining the consumption characteristics of the population is as follows: ； ； ； In the formula, Indicates the consumption characteristics of the population. This represents the total number of people in the crowd profile. Indicates the first 1 eigenvalue, Indicates the first The coefficients corresponding to each eigenvalue; This is the preset correction factor; Indicates from set Choose any A subset consisting of the value intervals of the mode. Represents a set The intersection of the various mode value intervals in the middle. express The first in The price range of the mode; , ; This represents finding the mean of the midpoint values ​​of the intersection.

7. The intelligent service system according to claim 6, characterized in that, The user profiling module includes: The information query unit is used to retrieve the usage information of any service unit based on the information input port; the usage information includes the number of users and the usage period. The personnel feature detection unit is used to obtain the personnel features of people entering and exiting the service unit based on cameras installed in public areas; The personnel characteristic statistics unit is used to statistically analyze the personnel characteristics of the service unit during the usage period based on the entry and exit status corresponding to each personnel characteristic, and to obtain a crowd profile as the crowd profile.

8. The intelligent service system according to claim 7, characterized in that, The personnel feature detection unit includes: The personnel tracking subunit is used to track personnel and locate their positions based on cameras installed in public areas. The contour recognition subunit is used to perform contour recognition on the personnel area and determine the upper garment area and lower garment area based on the relative position of each contour in the personnel area. The object recognition subunit is used to recognize objects in the upper garment area and the lower garment area, query the mode price range of the object recognition results, and use the mode price range as a personnel feature. The term "mode price range" refers to the mode of the price ranges corresponding to all identification results.

Images