Method, device, equipment and medium for determining positioning results
By combining the confidence evaluation characteristics of various positioning methods, the problem of low positioning accuracy in the prior art is solved, and higher positioning accuracy and reliability are achieved.
Patent Information
- Application Number
- CN202410547253.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-05-06
- Publication Date
- 2024-11-19
- Estimated Expiration
- 2044-05-06
AI Technical Summary
In the existing positioning technology, the priority selection of positioning methods leads to the problem of low positioning accuracy.
The position information of the target object is obtained based on at least two positioning methods, and the confidence evaluation feature and pre-trained confidence determination model is determined, the position information confidence of each positioning method is evaluated, and the target positioning result of the target object is finally determined.
The positioning accuracy and reliability are improved. By combining the characteristics of each positioning method, the confidence evaluation characteristics are extracted and the position information confidence of the positioning method is evaluated, thereby improving the accuracy of the final positioning result.
Smart Images

Figure CN118474670B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of computer processing technology, and in particular to a method, device, equipment and medium for determining a positioning result. Background Art
[0002] With the development of mobile communications, people's communication needs are met, and at the same time, higher requirements are placed on the services in the communication process. In order to provide more effective services, it is usually necessary to locate the object to improve the service quality based on the positioning results.
[0003] The current positioning technologies mainly include home broadband address positioning, MR (Measurement Report) triangulation positioning, MDT (Minimization Drive Test) positioning, base station positioning, satellite positioning, etc. Usually, a single positioning technology is used for positioning, or multiple positioning technologies are judged based on the positioning priority to determine the positioning technology that can be used, and positioning is performed based on the selected positioning technology. This method may result in the situation that the positioning technology with a low priority is not used, but its positioning result is more accurate, resulting in the problem of low positioning accuracy. Summary of the invention
[0004] The present invention provides a method, device, equipment and medium for determining a positioning result, so as to achieve the technical effect of improving positioning accuracy and reliability.
[0005] According to one aspect of the present invention, a method for determining a positioning result is provided, the method comprising:
[0006] Acquiring location information of a target object based on at least two positioning methods;
[0007] For each location information obtained by the positioning method, determine the confidence assessment feature corresponding to the location information, input the confidence assessment feature into a pre-trained confidence determination model, and obtain the confidence of the location information; wherein different confidence determination models are trained based on confidence sample features corresponding to the location information determined by different positioning methods and confidence labels corresponding to the confidence sample features;
[0008] Based on each of the confidence levels, a target positioning result corresponding to the target object is determined from all of the position information.
[0009] According to another aspect of the present invention, there is provided a device for determining a positioning result, the device comprising:
[0010] A location information acquisition module, used to acquire location information of a target object based on at least two positioning methods;
[0011] A confidence determination module, for determining, for each location information obtained by the positioning method, a confidence assessment feature corresponding to the location information, and inputting the confidence assessment feature into a pre-trained confidence determination model to obtain the confidence of the location information; wherein different confidence determination models are trained based on confidence sample features corresponding to the positioning information determined by different positioning methods and confidence labels corresponding to the confidence sample features;
[0012] The target positioning result determination module is used to determine the target positioning result corresponding to the target object from all the position information based on each of the confidence levels.
[0013] According to another aspect of the present invention, there is provided an electronic device, the electronic device comprising:
[0014] at least one processor; and
[0015] a memory communicatively connected to the at least one processor; wherein,
[0016] The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the method for determining the positioning result described in any embodiment of the present invention.
[0017] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the method for determining a positioning result described in any embodiment of the present invention when executed.
[0018] The technical solution of the embodiment of the present invention obtains the location information of the target object based on at least two positioning methods; determines the confidence assessment features corresponding to the location information, and inputs the confidence assessment features into a pre-trained confidence determination model to obtain the confidence of the location information; based on each confidence, determines the target location result corresponding to the target object from all the location information, thereby solving the problem of low positioning accuracy caused by selecting a positioning method for positioning based on the priority of the positioning method in the prior art, and realizes that the confidence assessment features corresponding to each location information are extracted respectively by combining the characteristics of the positioning method with respect to the location information obtained by each positioning method, and are used to evaluate the confidence of the location information determined by the corresponding positioning method, thereby improving the accuracy of the positioning confidence determination, and at the same time, combining each confidence, determining the target location result corresponding to the target object from the location information, thereby achieving the technical effect of improving positioning accuracy and reliability.
[0019] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS
[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.
[0021] Figure 1 is a flowchart of a method for determining a positioning result provided according to Embodiment 1 of the present invention;
[0022] Figure 2 is a schematic diagram of a method for determining a positioning result according to Embodiment 1 of the present invention;
[0023] Figure 3 is a flowchart of a method for determining a positioning result provided according to Embodiment 2 of the present invention;
[0024] Figure 4 is a schematic diagram of a method for determining a positioning result according to Embodiment 2 of the present invention;
[0025] Figure 5 is a flowchart of a method for determining a positioning result provided according to Embodiment 3 of the present invention;
[0026] Figure 6 is a flowchart of a method for determining a positioning result provided according to Embodiment 4 of the present invention;
[0027] Figure 7 is a flowchart of a method for determining a positioning result provided according to Embodiment 5 of the present invention;
[0028] Figure 8 is a structural schematic diagram of a device for determining a positioning result according to Embodiment 6 of the present invention;
[0029] Fig. 9 It is a structural schematic diagram of an electronic device for implementing the method for determining a positioning result according to an embodiment of the present invention. DETAILED DESCRIPTION
[0030] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.
[0031] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention 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 data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.
[0032] Embodiment 1
[0033] Figure 1 1 is a flowchart of a method for determining a positioning result according to Embodiment 1 of the present invention. This embodiment is applicable to the case of determining a positioning result. The method can be executed by a positioning result determining device. The positioning result determining device can be implemented in the form of hardware and / or software. The positioning result determining device can be configured in a computing device. Figure 1 As shown, the method includes:
[0034] S110: Acquire location information of a target object based on at least two positioning methods.
[0035] The target object may be an object that needs to be positioned, and the object may be an object, a device, or an individual.
[0036] In this embodiment, the positioning methods for acquiring the location information of the target object may include but are not limited to the following two positioning methods.
[0037] As an optional method, the positioning method can be a positioning method based on a broadband address. In the process of obtaining the location information of the target object based on the positioning method of the broadband address, the broadband address corresponding to the target object can be determined, and then the broadband address is converted into broadband longitude and latitude, and the broadband longitude and latitude are used as the location information of the target object. For example, the broadband installation address of the target object A is obtained as the broadband address. At this time, the broadband address cannot directly provide longitude and latitude information, and the address library can be used to convert the broadband address into longitude and latitude.
[0038] As another optional method, the positioning method can also be a positioning method based on an indoor distribution system. In the process of obtaining the location information of the target object based on the positioning method of the indoor distribution system, a measurement report reported by the device terminal of the target object in the indoor distribution system can be obtained. Through the measurement report, the high-frequency indoor cell corresponding to the target object is determined, and the longitude and latitude of the high-frequency indoor cell are used as the location information of the target object.
[0039] Among them, the indoor distribution system can be a system based on an indoor distribution network. The indoor distribution system uses an indoor antenna distribution system to evenly distribute the base station signal in every corner of the room, thereby ensuring that every area in the room can achieve ideal signal coverage. The cell covered by the indoor distribution system is called an indoor distribution cell. The device terminal being in the indoor distribution system can be understood as the device terminal moving into the range of the indoor distribution system. The measurement report (MR) can be a report file generated by a base station or terminal based on a certain period or event trigger report. For example, the measurement report is generated by a mobile station (Mobile Station, MS) to provide detailed information about the current wireless environment status to the network side (such as a base transceiver station). For example, the MS continuously or periodically measures the signals in its wireless environment, including the measurement of the signal strength, signal quality and other related parameters of different base stations. Based on these measurement results, the MS can generate a measurement report. The measurement report can include downlink signal information and uplink signal information, etc.
[0040] In this embodiment, when the device terminal of the target object is in the indoor distribution system, the device terminal can report a measurement report according to the frequency information sent by the base station, and the measurement report contains the latitude and longitude of the indoor cell where the device terminal is located. Obtain the measurement report, and determine the high-frequency indoor cell from all the indoor cells where the device terminal is located. For example, the number of days that the device terminal is in each indoor cell can be counted, and the indoor cell with the highest number of days can be used as the high-frequency indoor cell; or, the number of days that the device terminal is in each indoor cell continuously can be counted, and the indoor cell corresponding to the highest number of consecutive days can be used as the high-frequency indoor cell; or, the number of days that the device terminal is in each indoor cell within a preset period can be counted, and the indoor cell with the highest number of days can be used as the high-frequency indoor cell. Exemplarily, the indoor cell where the device terminal is in the most days in the month is used as the high-frequency indoor cell. Further, the longitude and latitude of the industrial parameters of the high-frequency indoor cell are used as the location information of the target object.
[0041] As another optional method, the positioning method can also be a minimized path test (MDT) positioning method. In the process of obtaining the location information of the target object based on the minimized path test positioning method, the MDT data reported by the terminal device of the target object can be obtained, and the location information of the target object can be determined based on the MDT data.
[0042] Specifically, the terminal device of the target object can report the wireless environment measurement information by measuring the wireless network, and the reported information is the MDT data. For example, the MDT data includes but is not limited to RSRP (Reference Signal Receiving Power), RSRQ (Reference Signal Receiving Quality), PHR (Power Headroom Report), etc. and the longitude and latitude information of the terminal device. The longitude and latitude information of the terminal device in the MDT data can be used as the location information of the target object.
[0043] As another optional method, the positioning method can also be a positioning method based on preset indicator features. In the process of obtaining the location information of the target object by using the positioning method based on preset indicator features, the positioning features corresponding to the target object can be determined according to the measurement report reported by the device terminal of the target object, and the location information of the target object can be determined based on the positioning features.
[0044] In this embodiment, the measurement report reported by the device terminal of the target object may include but is not limited to at least one of the following feature data: service cell identifier, physical cell identifier (PCI) of the service cell, service cell frequency, service cell RSRP, received signal code power (RSCP) of the service cell, neighboring cell PCI, neighboring cell frequency and neighboring cell RSRP, etc. These feature data can be used as positioning features of the target object. The positioning features of the target object can be compared with the indicator features in the pre-created feature library, and the preset positioning result corresponding to the indicator feature with the highest similarity to the positioning features of the target object can be used as the location information of the target object. Alternatively, a positioning model can be trained based on the indicator features in the feature library and the corresponding preset positioning results, and the positioning features of the target object are processed by the positioning model to obtain the location information of the target object.
[0045] Optionally, the positioning method may also be a satellite-based positioning method, a base station-based positioning method, a WiFi (Wireless Fidelity, wireless network)-based positioning method, a Bluetooth-based positioning method, and a sensor-based positioning method (such as an accelerometer, a gyroscope, etc.). It should be noted that, since different positioning methods may have different positioning accuracy, positioning coverage, interference conditions, and usage conditions, the location information of the target object obtained based on different positioning methods may be the same or different, and some location information may have high accuracy, while some location information may have low accuracy. For example, the broadband address used by the broadband address-based positioning method is usually manually entered, and the entered address may contain errors or omissions, resulting in a large deviation between the longitude and latitude parsed by the address library and the actual position, resulting in positioning errors. For example, the positioning method based on the indoor distribution system may have certain positioning errors because the indoor distribution system does not cover the indoor area of some indoor distribution cells. Based on this, the technical solution provided in this embodiment can evaluate the accuracy of each location information after obtaining the location information of the target object determined by different positioning methods, and determine the final positioning result corresponding to the target object based on the accuracy, thereby improving positioning accuracy and reliability.
[0046] S120. For the location information obtained by each positioning method, determine the confidence assessment features corresponding to the location information, input the confidence assessment features into a pre-trained confidence determination model, and obtain the confidence of the location information.
[0047] Among them, the confidence can be used to characterize the credibility and reliability of the location information, and can be expressed in numerical values, percentages or levels. For example, when the confidence is 100, it means that the credibility of the location information is very high, and the positioning is considered to be very accurate; the lower the confidence, the less credible the location information is, and the less accurate the positioning is. The confidence assessment feature may refer to a feature used to assess the confidence of the location information. Different confidence determination models are trained based on the confidence sample features corresponding to the positioning information determined by different positioning methods and the confidence labels corresponding to the confidence sample features. The confidence label can be used to indicate the accuracy of the real positioning information. A positioning method corresponds to a confidence determination model, and the confidence determination model is used to determine the confidence of the location information determined based on this positioning method. It should be noted that the method for determining the confidence of the location information obtained by each positioning method is the same, and can be introduced by taking the determination of the confidence of the location information obtained by any positioning method as an example.
[0048] In this embodiment, for the location information obtained by a certain positioning method, the confidence assessment feature corresponding to the location information can be determined first, and then the confidence assessment feature can be used as the input of the confidence determination model corresponding to the positioning method to evaluate the positioning accuracy of the location information and obtain the confidence of the location information. Correspondingly, in this way, the confidence of the location information obtained by each positioning method can be obtained. It should be noted that the positioning accuracy and precision of different positioning technologies are related to the quality of the sampled data and the location characteristics, and the confidence assessment features used to determine the confidence of the location information obtained by different positioning methods are different.
[0049] In this embodiment, determining the confidence assessment feature corresponding to the location information includes: determining the confidence assessment feature corresponding to the location information based on at least one of the location information, a measurement report reported by a terminal device of the target object, and predetermined map data.
[0050] In practical applications, at least one item of information corresponding to each positioning method can be selected from the location information, the measurement report reported by the terminal device of the target object, and the predetermined map data, and then, the feature extraction of at least one item of information corresponding to the positioning method is performed to obtain the confidence assessment feature corresponding to the location information obtained based on the positioning method. For example, if the positioning method is a broadband address-based positioning method, the longitude and latitude information of the service cell closest to the location information in the measurement report can be extracted as the confidence assessment feature; or the position difference between the closest service cell and the location information can be used as the confidence assessment feature.
[0051] The technical solution provided in this embodiment extracts the confidence assessment features corresponding to each position information from the position information obtained by each positioning method in combination with the characteristics of the positioning method, which are used to evaluate the confidence of the position information determined by the corresponding positioning method, thereby improving the accuracy of the positioning confidence determination and further improving the accuracy of the final positioning result determination.
[0052] S130 . Based on each confidence level, determine a target positioning result corresponding to the target object from all the position information.
[0053] In this embodiment, the position information corresponding to the maximum confidence among all the confidences can be used as the target positioning result of the target object; or, partial confidences can be selected from all the confidences, and the position information corresponding to the selected partial confidences can be fused to obtain the fused position information as the target positioning result of the target object; or, the position information corresponding to the positioning method with the highest priority among the partial confidences can be used as the target positioning result. Optionally, the method of selecting partial confidences can be: sorting all confidences from high to low, selecting a preset number of confidences in the front as partial confidences; or, using confidences greater than a preset threshold as partial confidences.
[0054] For example, see Figure 2 , based on multiple location information corresponding to object 1 given by different positioning methods, including 92% confidence of location information 1 determined by positioning method 1, 80% confidence of location information 1 determined by positioning method 2, 62% confidence of location information 2 determined by positioning method 3, and 72% confidence of location information 3 determined by positioning method 4, the location information 1 with the highest confidence (92%) is selected as the target positioning result of object 1. It should be noted that when different positioning methods are used to obtain the same location information of the target object, the confidence of the same location information can also be weighted averaged, and the obtained average value is used as the confidence of the location information. The target positioning result of the target object is determined by the confidence of the location information of different locations, thereby improving the positioning accuracy.
[0055] The technical solution of this embodiment obtains the location information of the target object based on at least two positioning methods; determines the confidence assessment features corresponding to the location information, and inputs the confidence assessment features into a pre-trained confidence determination model to obtain the confidence of the location information; based on each confidence, determines the target positioning result corresponding to the target object from all the location information, which solves the problem of low positioning accuracy caused by selecting a positioning method for positioning based on the priority of the positioning method in the prior art, and realizes the extraction of confidence assessment features corresponding to each location information by combining the characteristics of the positioning method with respect to the location information obtained by each positioning method, and is used to evaluate the confidence of the location information determined by the corresponding positioning method, thereby improving the accuracy of the positioning confidence determination and, in combination with each confidence, determining the target positioning result corresponding to the target object from the location information, thereby achieving the technical effect of improving positioning accuracy and reliability.
[0056] Embodiment 2
[0057] Figure 3 This is a flowchart of a method for determining a positioning result according to the second embodiment of the present invention. On the basis of the above embodiment, when the positioning method includes a positioning method based on a broadband address, the confidence assessment feature corresponding to the location information obtained by the positioning method based on the broadband address can be determined based on the location information, the measurement report reported by the terminal device of the target object, and the predetermined map data. The specific implementation method can refer to the technical solution of this embodiment. Among them, the technical terms that are the same as or corresponding to the above embodiment are not repeated here.
[0058] like Figure 3 As shown, the method specifically comprises the following steps:
[0059] S210: When the positioning method includes a positioning method based on a broadband address, determine a first electronic fence based on predetermined map data and location information, and determine a first shortest distance from the location information to the first electronic fence.
[0060] The map data includes at least one pre-set electronic fence. The electronic fence can be a range, forming a fenced area. The range of the fence setting can be as small as a point or as large as a market, a building, a city, etc., without specific limitations, and can be set by technicians according to actual work conditions. For example, multiple fences are set along an existing wall (such as a brick wall, a concrete wall or an iron fence), and multiple fences are set in the map data, which is called an electronic fence.
[0061] In this embodiment, the electronic fence closest to the location information can be matched from at least one electronic fence in the map data, and the electronic fence closest to the location information is used as the first electronic fence. If the location information is within the first electronic fence, the first closest distance from the location information to the first electronic fence is 0, that is, the first closest distance is 0; if the location information is outside the first electronic fence, the closest distance from the location information to the first electronic fence is used as the first closest distance.
[0062] S220. Determine at least one serving cell and the cell location of the serving cell based on the measurement report reported by the terminal device of the target object.
[0063] The measurement report includes location information of at least one serving cell to be selected.
[0064] In this embodiment, the measurement report reported by the terminal device of the target object is obtained, and one or more service cells can be selected from at least one service cell to be selected in the measurement report based on a preset screening rule. For example, the service cell in which the terminal device is in the most days in the month is selected from at least one service cell to be selected, or the service cell in which the terminal device is in the top three days (sorted from large to small) in the month is selected. The cell location of each service cell is obtained according to the location information of the service cell in the measurement report.
[0065] S230: Determine a confidence assessment feature corresponding to the location information based on the first closest distance, the location deviation between each cell location and the location information, and the similarity between the location information and the broadband address of the target object.
[0066] Among them, the position deviation can be used to indicate the degree of deviation between two positions. The larger the position deviation, the greater the position difference. Conversely, the smaller the position difference, the closer the positions are. Similarity indicates the degree of similarity between two positions. The higher the similarity, the closer the positions are. Conversely, the lower the similarity, the less similar the positions are.
[0067] In this embodiment, the location information obtained by the broadband address-based positioning method is determined based on the broadband address of the target object, and a similarity algorithm can be used to calculate the similarity between the location information and the broadband address of the target object. Optionally, the similarity algorithm can be a character matching algorithm, and the character matching algorithm includes but is not limited to an algorithm based on edit distance, an algorithm based on n-gram, and an algorithm based on rules (such as regular expressions).
[0068] In this embodiment, the method for determining the position deviation between each cell position and the position information can be: for each cell position, based on the difference value between the position information and the cell position and the TA (Timing.Advance) unit distance and TA value in the measurement report, determine the position deviation between the cell position and the position information.
[0069] It should be noted that in a wireless communication system, due to the limited propagation speed of electromagnetic waves, there will be a certain time delay for the signal to be transmitted from the base station to the UE and back to the base station. In order to compensate for this delay, the UE's transmission time needs to be adjusted. This adjustment process is achieved through the TA value to ensure that the signal can accurately reach the base station within a predetermined time window. Among them, the TA value refers to the amount of time that the system frame of the user terminal (User Equipment, UE) sends uplink data ahead of the corresponding downlink frame. That is, the TA value can be used to reflect the time advance between the UE and the base station. The TA unit distance can be understood as the distance corresponding to each unit of the TA value sampled in the measurement report, which is related to the cell subcarrier spacing (Subcarrier Spacing, SCS). For example, if SCS = 15KHz, the TA unit distance is 78.125 meters, and if SCS = 30KHz, the TA unit distance is 39.0625 meters.
[0070] Specifically, the difference between the location information and the cell location can be processed as a quotient with the TA unit distance in the measurement report, and the median of the TA value can be subtracted from the obtained quotient, and the obtained difference can be used as the location deviation. Accordingly, the location deviation between each cell location and the location information can be obtained. Exemplarily, the location deviation between the cell location and the location information = (location information - cell location) / TA unit distance - median TA value.
[0071] On the basis of the above technical solution, the first closest distance, all position deviations and similarities can be processed, such as splicing or fusion processing, and the processed feature information can be used as the confidence assessment feature corresponding to the location information. Alternatively, one or part of the position deviations (such as selecting the minimum position deviation) is selected from all the position deviations, and the selected position deviations and the first closest distance and similarity are processed to obtain the confidence assessment feature corresponding to the location information. Exemplarily, the confidence assessment features include the similarity between the home broadband address and the location information (feature 1), the distance between the location information and the nearest fence area (feature 2), and the position deviation between the location information and the cell location (feature 3). After determining the confidence assessment feature corresponding to the location information determined based on the broadband address, the confidence assessment feature can be input into the confidence determination model corresponding to the positioning method based on the broadband address to obtain the confidence of the location information. Prior to this, the confidence determination model corresponding to the positioning method based on the broadband address can also be pre-trained.
[0072] In this embodiment, the positioning information of at least one object determined in a broadband address-based positioning method can be obtained, and the confidence sample features corresponding to each positioning information and the confidence labels corresponding to the confidence sample features can be determined to obtain a first training sample. The confidence determination model to be trained is trained using the first training sample to obtain a confidence determination model corresponding to the broadband address-based positioning method. The method of determining the confidence sample features is similar to the method of determining the confidence assessment features corresponding to the location information when the positioning method includes a broadband address-based positioning method, and will not be described in detail here.
[0073] It should be noted that in order to avoid the numerical granularity being too small and the number of real samples being too large, after determining the confidence sample features corresponding to each positioning information, the confidence sample features can be screened based on the set interval corresponding to the preset feature index to obtain the screened confidence sample features, and the confidence determination model corresponding to the broadband address-based positioning method can be obtained by training the screened confidence sample features and their corresponding confidence labels.
[0074] Among them, the preset characteristic indicators include a first distance indicator (indicating the distance between the positioning information and the nearest fence area), a deviation indicator (indicating the position deviation between the positioning information and the cell location) and a similarity indicator (indicating the similarity between the home broadband address and the positioning information).
[0075] For example, see Figure 4,The confidence sample features include the similarity between the home broadband address and the ,positioning information (feature 1), the distance between the positioning information and the nearest ,fenced area (feature 2), and the position deviation between the positioning information and the ,cell location (feature 3). The setting intervals corresponding to the similarity index are: 100%, (100, 80%], (80%, 0%]; the setting intervals corresponding to the deviation index are: 0, 1, [2, 10]; the setting intervals corresponding to the first distance index are: 0, (0-100], (100, 300]. If there are features in the confidence sample features that exceed the interval setting range, the confidence sample features are removed and the remaining confidence sample features are used for model training. In other words, the home broadband address that exceeds the interval setting range is considered to be an invalid address and is not used for positioning, which effectively improves the sample quality and the model accuracy. Based on this, the accuracy of different features under different interval combinations can be statistically analyzed according to the accuracy distribution corresponding to different confidence sample features. When a new object is located using a confidence determination model, its positioning prediction accuracy can be obtained based on its feature combination, and used as the confidence of the new object positioning information.
[0076] The technical solution of this embodiment determines the first electronic fence and the first closest distance from the location information to the first electronic fence based on the predetermined map data and location information when the positioning method includes a positioning method based on a broadband address. At the same time, based on the measurement report reported by the terminal device of the target object, at least one service cell and the cell position of the service cell are determined. Furthermore, the confidence assessment feature is determined in combination with the first closest distance, the position deviation between each cell position and the location information, and the similarity between the location information and the broadband address of the target object, so that the confidence of the location information obtained by the positioning method based on the broadband address is determined by the confidence assessment feature, thereby improving the accuracy of the positioning confidence determination.
[0077] Embodiment 3
[0078] Figure 5 This is a flowchart of a method for determining a positioning result provided according to Embodiment 3 of the present invention. On the basis of the aforementioned embodiment, when the positioning method includes a positioning method based on an indoor distribution system, the confidence assessment feature corresponding to the location information obtained by the positioning method based on the indoor distribution system can be determined based on the location information, the measurement report reported by the terminal device of the target object, and the predetermined map data. The specific implementation method can refer to the technical solution of this embodiment. Among them, the technical terms that are the same as or corresponding to the aforementioned embodiments are not repeated here.
[0079] like Figure 5 As shown, the method specifically comprises the following steps:
[0080] S310: When the positioning method includes a positioning method based on an indoor distribution system, determine a second electronic fence based on predetermined map data and location information, and determine a second shortest distance from the location information to the second electronic fence.
[0081] In this embodiment, the method for determining the second electronic fence is similar to the method for determining the first electronic fence, and the method for determining the second closest distance from the location information to the second electronic fence is similar to the method for determining the first closest distance from the location information to the first electronic fence, which will not be repeated here.
[0082] S320. Based on the measurement report reported by the terminal device of the target object, determine the time advance between the terminal device and the base station and the first accumulated number of days that the location information is located in the second electronic fence.
[0083] The measurement report includes at least one timing advance, which refers to a TA value.
[0084] In this embodiment, a measurement report reported by a terminal device of the target object is obtained, and a TA value between the terminal device and the base station is extracted from the measurement report to obtain a time advance. The total number of days in the second electronic fence is counted by measuring the time when the location information in the report is in the second electronic fence, and used as the first cumulative number of days.
[0085] S330: Determine a confidence assessment feature corresponding to the location information based on the second closest distance, the time advance, and the first cumulative number of days.
[0086] In this embodiment, the combined feature of the second closest distance, the time advance, and the first cumulative number of days can be used as the confidence assessment feature corresponding to the location information. Alternatively, the median of all time advances is calculated, and the combined feature of the second closest distance, the median, and the first cumulative number of days is used as the confidence assessment feature corresponding to the location information. Exemplarily, the confidence assessment features include the median of the TA value (feature 1), the distance between the location information and the nearest fence area (feature 2), and the number of days from the location information to the nearest fence (feature 3). After determining the confidence assessment feature corresponding to the location information, the confidence assessment feature can be input into a confidence determination model corresponding to the positioning method based on the indoor distribution system to obtain the confidence of the location information. Prior to this, a confidence determination model corresponding to the positioning method based on the indoor distribution system can also be pre-trained.
[0087] In this embodiment, the positioning information of at least one object determined in a positioning method based on an indoor distribution system can be obtained, and the confidence sample features corresponding to each positioning information and the confidence labels corresponding to the confidence sample features can be determined to obtain a second training sample. The confidence determination model to be trained is trained using the second training sample to obtain a confidence determination model corresponding to the positioning method based on an indoor distribution system. The method of determining the confidence sample features is similar to the method of determining the confidence assessment features corresponding to the location information when the positioning method includes a positioning method based on an indoor distribution system, and will not be described in detail here.
[0088] It should be noted that in order to avoid the numerical granularity being too small and the number of real samples being too large, after determining the confidence sample features corresponding to each positioning information, the confidence sample features can be screened based on the set interval corresponding to the preset feature index to obtain the screened confidence sample features, and the confidence determination model corresponding to the positioning method based on the indoor distribution system can be obtained by training the screened confidence sample features and their corresponding confidence labels.
[0089] Among them, the preset characteristic indicators include the second distance indicator, the TA median indicator, and the first day number indicator (indicating the number of days from the positioning information to the nearest fence).
[0090] Exemplarily, the setting interval corresponding to the second distance index is: 0, (0-100], (100, 300]; the setting interval corresponding to the first day index is: 1, [2-5), [5, 31]; the setting interval corresponding to the TA median index is: 0, 1, [2, 10]. If there are features in the confidence sample features that exceed the interval setting range, the confidence sample features are removed, and the remaining confidence sample features are used for model training, thereby improving the quality of sample features, improving model accuracy, and improving model training speed.
[0091] The technical solution of this embodiment is to determine the second electronic fence and the second closest distance from the location information to the second electronic fence based on the predetermined map data and location information when the positioning method includes a positioning method based on an indoor distribution system. Further, based on the measurement report reported by the terminal device of the target object, the time advance between the terminal device and the base station and the first cumulative number of days that the location information is located in the second electronic fence are determined. In combination with the second closest distance, the time advance and the first cumulative number of days, the confidence assessment feature corresponding to the location information is determined, so that the confidence of the location information obtained by the positioning method based on the indoor distribution system is determined by the confidence assessment feature, thereby improving the accuracy of the location confidence determination.
[0092] Embodiment 4
[0093] Figure 6This is a flowchart of a method for determining a positioning result provided in accordance with Embodiment 4 of the present invention. Based on the above embodiments, when the positioning method includes a positioning method that minimizes the path measurement, the confidence assessment feature corresponding to the location information obtained based on the positioning method that minimizes the path measurement can be determined based on the location information, the measurement report reported by the terminal device of the target object, and the predetermined map data. The specific implementation method can refer to the technical solution of this embodiment. Among them, the technical terms that are the same as or corresponding to the above embodiments are not repeated here.
[0094] like Figure 6 As shown, the method specifically comprises the following steps:
[0095] S410: When the positioning method includes minimizing the route measurement positioning method, a third electronic fence is determined based on predetermined map data and location information, and a third shortest distance from the location information to the third electronic fence is determined.
[0096] In this embodiment, the method for determining the third electronic fence is similar to the method for determining the first electronic fence, and the method for determining the third closest distance from the location information to the third electronic fence is similar to the method for determining the first closest distance from the location information to the first electronic fence, which will not be repeated here.
[0097] S420: Determine the second accumulated number of days that the location information is located in the third electronic fence based on the measurement report reported by the terminal device of the target object.
[0098] In this embodiment, the method of determining the second accumulated number of days that the location information is located in the third area is similar to the method of determining the first accumulated number of days that the location information is located in the second electronic fence, and will not be described in detail here.
[0099] S430: Determine a confidence assessment feature corresponding to the location information based on the location information, the third closest distance, and the second cumulative number of days.
[0100] In this embodiment, the combined feature of the location information, the third closest distance, and the second cumulative number of days can be used as the confidence assessment feature corresponding to the location information. For example, the confidence assessment feature includes the location information (feature 1), the distance between the location information and the nearest fence area (feature 2), and the number of days from the location information to the nearest fence (feature 3). After determining the confidence assessment feature, the confidence assessment feature can be input into a confidence determination model corresponding to the positioning method based on minimization of the route measurement to obtain the confidence of the location information. Prior to this, the confidence determination model corresponding to the positioning method based on minimization of the route measurement can also be pre-trained.
[0101] In this embodiment, the positioning information of at least one object determined in the positioning method based on minimization of path measurement can be obtained, and the confidence sample features corresponding to each positioning information and the confidence labels corresponding to the confidence sample features can be determined to obtain the second training samples. The confidence determination model to be trained is trained by the second training samples to obtain the confidence determination model corresponding to the positioning method based on minimization of path measurement. The method of determining the confidence sample features is similar to the method of determining the confidence assessment features corresponding to the position information when the positioning method includes the positioning method based on minimization of path measurement, and will not be described in detail here.
[0102] It should be noted that in order to avoid too small a numerical granularity and too many real samples, after determining the confidence sample features corresponding to each positioning information, the confidence sample features can be screened based on the set interval corresponding to the preset feature index to obtain the screened confidence sample features, so as to obtain the confidence determination model corresponding to the minimized path measurement positioning method through the screened confidence sample features and their corresponding confidence labels. Among them, the preset feature index includes the third distance index and the second number index.
[0103] Exemplarily, the setting interval corresponding to the third distance indicator is: 0, (0-100], (100, 300]; the setting interval corresponding to the second digit indicator is: 1, 2-5, 5+. If there are features in the confidence sample features that exceed the interval setting range, the confidence sample features are removed, and the remaining confidence sample features are used for model training, thereby improving the quality of the sample features, improving the model accuracy, and increasing the model training speed.
[0104] The technical solution of this embodiment determines, when the positioning method includes a minimized route measurement positioning method, a third electronic fence based on predetermined map data and location information, and determines a third closest distance from the location information to the third electronic fence, and then determines the second cumulative number of days that the location information is located in the third electronic fence based on a measurement report reported by a terminal device of the target object, and determines a confidence assessment feature corresponding to the location information based on the location information, the third closest distance, and the second cumulative number of days, so that the confidence of the location information obtained based on the minimized route measurement positioning method is determined through the confidence assessment feature, thereby improving the accuracy of the positioning confidence determination.
[0105] Embodiment 5
[0106] Figure 7It is a flowchart of a method for determining a positioning result provided according to Embodiment 5 of the present invention. On the basis of the above-mentioned embodiment, when the positioning method includes a positioning method based on preset indicator features, the confidence assessment feature corresponding to the location information obtained by the positioning method based on the preset indicator features can be determined according to the measurement report reported by the terminal device of the target object. The specific implementation method can refer to the technical solution of this embodiment. Among them, the technical terms that are the same as or corresponding to the above-mentioned embodiments are not repeated here.
[0107] like Figure 7 As shown, the method specifically comprises the following steps:
[0108] S510: When the positioning method includes a positioning method based on a preset indicator feature, determine target attribute data corresponding to the preset indicator based on a measurement report reported by a terminal device of the target object.
[0109] Among them, the preset indicators at least include the target location of the terminal device and the time advance between the terminal device and the base station; the target location includes the service cell and the neighboring cell. It should be noted that the concepts of "service cell" and "neighboring cell" are relative, not absolute. For example, for a certain communication, cell A among many cells is the service cell, and cell B and cell C are neighboring cells; but for the next communication, cell B may be the service cell, and cell A and cell C may be the neighboring cells. It should also be noted that neighboring cells refer to cells that can be switched with each other during the communication process, not geographically adjacent cells.
[0110] In this embodiment, the measurement report reported by the terminal device of the target object can be obtained, and the characteristic data corresponding to each preset indicator can be extracted from the measurement report as the target attribute data. For example, the target attribute data includes but is not limited to at least one of the following: a serving cell identifier, a physical cell identifier of a serving cell, a serving cell frequency, a reference signal received power RSRP of a serving cell, an RSCP of a serving cell, a neighboring cell PCI, a neighboring cell frequency, a neighboring cell RSRP and a TA value, etc.
[0111] S520: Determine confidence assessment features corresponding to the location information based on the target attribute data.
[0112] In this embodiment, all target attribute data can be used as confidence assessment features corresponding to the location information; or, based on a preset screening rule, some target attribute data can be screened out from all target attribute data as confidence assessment features corresponding to the location information. For example, the screening rule can be to screen the reference signal received power of RSRP within a preset power range, screen the TA value within a preset TA range, and so on. Alternatively, the target attribute data can be pre-processed based on a preset data processing method, and the processed target attribute data can be used as a confidence assessment feature corresponding to the location information. For example, the level value of the neighboring cell can be converted based on the level value of the serving cell, such as replacing the level value of the neighboring cell with the level value of the serving cell, or replacing the level value of the neighboring cell with the difference between the level value of the neighboring cell and the level value of the serving cell, and the converted level value can be used as the target attribute data. After determining the confidence assessment feature, the confidence assessment feature can be input into a confidence determination model corresponding to the positioning method based on the preset indicator feature to obtain the confidence of the location information. Prior to this, a confidence determination model corresponding to the positioning method based on the preset indicator feature can also be pre-trained.
[0113] In this embodiment, before the confidence assessment feature is input into the pre-trained confidence determination model, it also includes: when the positioning method includes a positioning method based on a preset indicator feature, obtaining the geographic location information of at least two objects determined in a positioning method based on a broadband address, and determining the confidence of each geographic location information; based on the confidence of each geographic location information and a preset first threshold, determining the feature objects to be collected from at least two objects; determining the indicator data corresponding to the preset indicator from the measurement report reported by the terminal device of each feature object to be collected; determining the confidence sample feature based on the indicator data and the concentration of at least one target fence determined in advance; training the confidence determination model to be trained based on the confidence sample feature and the confidence label corresponding to the confidence sample feature to obtain a trained confidence determination model.
[0114] The degree of aggregation can be used to indicate how densely the objects in the fence are distributed. For example, the higher the degree of aggregation, the more concentrated the objects in the fence are distributed, and the lower the degree of aggregation, the more dispersed the objects in the fence are distributed.
[0115] In this embodiment, some objects can be screened out from at least two objects according to the confidence corresponding to the geographic location information of each object determined in a broadband address-based positioning method, and the screened objects are used as feature objects to be collected. For example, objects corresponding to the geographic location information having a confidence greater than or equal to a preset first threshold are selected as feature objects to be collected. Further, indicator data corresponding to preset indicators can be extracted from the measurement reports reported by the terminal devices of each feature object to be collected. The indicator data and the concentration of at least one target fence can be feature spliced to obtain confidence sample features, and a corresponding confidence label can be assigned to each confidence sample feature. Further, based on the confidence sample features and the confidence labels corresponding to the confidence sample features, the confidence determination model to be trained is trained to obtain a trained confidence determination model.
[0116] The advantage of this setting is that by determining the confidence of the geographic location information based on the home broadband address, objects corresponding to the geographic location information with high confidence are screened out, and the indicator data corresponding to these objects are extracted. This can increase the credible feature samples of indoor objects and improve the accuracy of positioning based on indicator data.
[0117] It should be noted that in order to avoid the numerical granularity being too small and the number of real samples being too large, after determining the confidence sample features, the confidence sample features can be screened based on the set interval corresponding to the preset feature index to obtain the screened confidence sample features, so as to obtain the confidence determination model corresponding to the positioning method based on the preset indicator features through the screened confidence sample features and their corresponding confidence labels. The preset feature indicators include preset indicators and concentration indicators. If there are features in the confidence sample features that exceed the interval setting range, the confidence sample features will be eliminated, and the remaining confidence sample features will be used for model training, thereby improving the quality of the sample features, improving the model accuracy, and increasing the model training speed.
[0118] In this embodiment, before determining the confidence sample features based on the indicator data and the predetermined concentration of at least one target fence, it also includes: for a single target fence, determining the area around the fence corresponding to the target fence; determining the third cumulative number of days in which the terminal location is located within the target fence within a preset time period, and the fourth cumulative number of days in which the terminal location is located in the area around the fence; if the third cumulative number of days reaches a preset second threshold, determining the concentration of the target fence based on the third cumulative number of days and the fourth cumulative number of days.
[0119] In this embodiment, the area within a preset distance around the target fence can be used as the area around the fence corresponding to the target fence, and the area around the fence is connected to the edge of the target fence. The cumulative number of days in which the terminal position is located in the target fence within the preset duration can be counted as the third cumulative number of days, and the cumulative number of days in which the terminal position is located in the area around the fence within the preset duration can be counted as the fourth cumulative number of days. If the third cumulative number of days reaches the preset second threshold, the ratio between the third cumulative number of days and the fourth cumulative number of days can be used as the concentration of the target fence. If the third cumulative number of days does not reach the preset second threshold, there is no need to calculate the concentration of the target fence, and the target fence can be removed from at least one target fence.
[0120] Exemplarily, assuming that the preset second threshold is 5, the concentration of the target fence is located = the number of days the target fence is located (i.e. the third cumulative number of days) / the total number of days the fence within 500 meters around the target fence is located (i.e. the fourth cumulative number of days), and the third cumulative number of days>=5.
[0121] It should be noted that due to the influence of various factors such as differences in device hardware, device software algorithms, environmental interference, individual interference, etc., in the actual measurement process, there are certain differences in the level values measured by different terminal devices at the same location, and this level difference is also reflected in the measurement levels of the service cell and the neighboring cell. If the Euclidean distance is directly used to calculate the similarity of the terminal measurement data, the Euclidean distance will be larger and the similarity will be lower, resulting in a problem of low accuracy of the calculation result, which leads to the problem of low model accuracy when directly using these measurement data to train the model.
[0122] In order to solve this problem, after determining the indicator data corresponding to the preset indicator, for the indicator data, a first level value when the same terminal device is in a service cell and a second level value when it is in a neighboring cell can be obtained; a level relative value is determined based on the first level value and the second level value, and the second level value in the indicator data is updated based on the level relative value.
[0123] In this embodiment, the first level value when the same terminal device is in the service cell and the second level value of the neighboring cell during the same communication process can be obtained from the index data, the difference between the first level value and the second level value is calculated, the difference is used as the level relative value, and the second level value is corrected by the level relative value. For example, the level relative value is used as the new second level value, and the second level value in the index data is updated to determine the confidence sample feature based on the updated index data and the concentration of at least one predetermined target fence. The advantage of such processing is that it can effectively reduce the impact of the difference in measurement levels of different terminals on the positioning accuracy of the index data, so that the measurement deviation between different terminals is reduced to a certain extent, and the similarity between different terminals can be more accurately represented, thereby improving the positioning accuracy.
[0124] For example, the indicator data in the measurement report reported by terminal A before the update is shown in Table 1, the indicator data in the measurement report reported by terminal B before the update is shown in Table 2, the indicator data corresponding to terminal A after the update is shown in Table 3, and the indicator data corresponding to terminal B before the update is shown in Table 4. The serving cell level value 61 before the update-the neighboring cell level value 55=6, the neighboring cell level value 55 is replaced by 6, that is, the neighboring cell level value after the update is 6.
[0125] Table 1 Indicator data in the measurement report reported by terminal A
[0126]
[0127] Table 2 Indicator data in the measurement report reported by terminal B
[0128]
[0129]
[0130] Table 3 Index data corresponding to terminal A after update
[0131]
[0132] Table 4 Updated indicator data corresponding to terminal B
[0133]
[0134] In the above example, the Euclidean distance between the indicator data of the two terminal devices A and B is calculated. The Euclidean distance before conversion is 5.29, and the Euclidean distance after conversion is 2, indicating that the similarity of the indicator data of the two devices has increased.
[0135] It should be noted that after determining the indicator data corresponding to the preset indicator from the measurement reports reported by the terminal devices of each feature object to be collected, a feature library can also be constructed based on the indicator data corresponding to the preset indicator, so that when determining the positioning feature of the target object, the positioning feature can be compared with the indicator feature in the feature library to obtain the location information of the target object. Alternatively, the indicator data corresponding to the preset indicator is added to the learning and training of the positioning model to process the positioning feature of the target object through the positioning model to obtain the location information of the target object.
[0136] The technical solution of this embodiment is to determine target attribute data corresponding to preset indicators based on a measurement report reported by a terminal device of the target object when the positioning method includes a positioning method based on preset indicator features; and further, determine a confidence assessment feature corresponding to the location information based on the target attribute data, so that the confidence of the location information obtained by the positioning method based on the preset indicator features is determined through the confidence assessment feature, thereby improving the accuracy of the positioning confidence determination.
[0137] Embodiment 6
[0138] Figure 8 FIG. 1 is a schematic diagram of a structure of a device for determining a positioning result according to Embodiment 6 of the present invention. Figure 8 As shown, the device includes: a location information acquisition module 610, a confidence determination module 620 and a target positioning result determination module 630.
[0139] Among them, the location information acquisition module 610 is used to obtain the location information of the target object based on at least two positioning methods; the confidence determination module 620 is used to determine the confidence assessment features corresponding to the location information obtained by each positioning method, and input the confidence assessment features into the pre-trained confidence determination model to obtain the confidence of the location information; wherein different confidence determination models are trained based on confidence sample features corresponding to the positioning information determined by different positioning methods and confidence labels corresponding to the confidence sample features; the target positioning result determination module 630 is used to determine the target positioning result corresponding to the target object from all the location information based on each confidence.
[0140] The technical solution of this embodiment obtains the location information of the target object based on at least two positioning methods; determines the confidence assessment features corresponding to the location information, and inputs the confidence assessment features into a pre-trained confidence determination model to obtain the confidence of the location information; based on each confidence, determines the target positioning result corresponding to the target object from all the location information, which solves the problem of low positioning accuracy caused by selecting a positioning method for positioning based on the priority of the positioning method in the prior art, and realizes the extraction of confidence assessment features corresponding to each location information by combining the characteristics of the positioning method with respect to the location information obtained by each positioning method, and is used to evaluate the confidence of the location information determined by the corresponding positioning method, thereby improving the accuracy of the positioning confidence determination and, in combination with each confidence, determining the target positioning result corresponding to the target object from the location information, thereby achieving the technical effect of improving positioning accuracy and reliability.
[0141] Based on the above device, optionally, the confidence determination module 620 includes a confidence assessment feature determination unit. The confidence assessment feature determination unit is used to determine a confidence assessment feature corresponding to the location information based on at least one of the location information, a measurement report reported by the terminal device of the target object, and predetermined map data.
[0142] On the basis of the above-mentioned device, optionally, the confidence assessment feature determination unit includes a first closest distance determination unit, a cell location determination unit and a first feature determination unit. The first closest distance determination unit is used to determine the first electronic fence and determine the first closest distance from the location information to the first electronic fence based on the predetermined map data and the location information when the positioning method includes a positioning method based on a broadband address; the cell location determination unit is used to determine at least one service cell and the cell location of the service cell based on the measurement report reported by the terminal device of the target object; wherein the measurement report includes the location information of at least one service cell to be selected; the first feature determination unit is used to determine the confidence assessment feature corresponding to the location information based on the first closest distance, the position deviation between each of the cell locations and the location information, and the similarity between the location information and the broadband address of the target object.
[0143] On the basis of the above device, optionally, the confidence assessment feature determination unit also includes a second closest distance, a first cumulative days determination unit and a second feature determination unit. The second closest distance determination unit is used to determine the second electronic fence and determine the second closest distance from the location information to the second electronic fence based on the predetermined map data and the location information when the positioning method includes a positioning method based on an indoor distribution system; the first cumulative days determination unit is used to determine the time advance between the terminal device and the base station and the first cumulative days that the location information is located in the second electronic fence based on the measurement report reported by the terminal device of the target object; wherein the measurement report includes at least one time advance; the second feature determination unit is used to determine the confidence assessment feature corresponding to the location information based on the second closest distance, the time advance and the first cumulative days.
[0144] On the basis of the above-mentioned device, the confidence assessment feature determination unit also includes a third closest distance, a second cumulative days determination unit and a third feature determination unit. The third closest distance determination unit is used to determine the third electronic fence and determine the third closest distance from the location information to the third electronic fence based on the predetermined map data and the location information when the positioning method includes the minimized route measurement positioning method; the second cumulative days determination unit is used to determine the second cumulative days that the location information is located in the third electronic fence based on the measurement report reported by the terminal device of the target object; the third feature determination unit is used to determine the confidence assessment feature corresponding to the location information based on the location information, the third closest distance and the second cumulative days.
[0145] On the basis of the above-mentioned device, the confidence assessment feature determination unit also includes a target attribute data determination unit and a fourth feature determination unit. The target attribute data determination unit is used to determine the target attribute data corresponding to the preset indicator based on the measurement report reported by the terminal device of the target object when the positioning method includes a positioning method based on the preset indicator feature; wherein the preset indicator at least includes the target location where the terminal device is located and the time advance between the terminal device and the base station; the target location includes a serving cell and a neighboring cell; the fourth feature determination unit is used to determine the confidence assessment feature corresponding to the location information based on the target attribute data.
[0146] On the basis of the above device, optionally, the device further comprises a model determination module, the model determination module comprising a geographic location information determination unit, a feature object determination unit to be collected, an indicator data determination unit, a confidence sample feature determination unit and a model determination unit. The geographic location information determination unit is used to obtain the geographic location information of at least two objects determined in a broadband address-based positioning method when the positioning method includes a positioning method based on preset indicator features, and determine the confidence of each of the geographic location information; the feature object determination unit to be collected is used to determine the feature object to be collected from the at least two objects based on the confidence of each of the geographic location information and a preset first threshold; the indicator data determination unit is used to determine the indicator data corresponding to the preset indicator from the measurement report reported by the terminal device of each of the feature objects to be collected; the confidence sample feature determination unit is used to determine the confidence sample feature based on the indicator data and the predetermined concentration of at least one target fence; the model determination unit is used to train the confidence determination model to be trained based on the confidence sample feature and the confidence label corresponding to the confidence sample feature to obtain the trained confidence determination model.
[0147] On the basis of the above device, optionally, the device further includes a fence surrounding area determination unit, a cumulative days determination unit and a concentration determination unit. The fence surrounding area determination unit is used to determine the fence surrounding area corresponding to the target fence for a single target fence; the cumulative days determination unit is used to determine the third cumulative days that the terminal position is located in the target fence within a preset time period, and the fourth cumulative days that the terminal position is located in the fence surrounding area; the concentration determination unit is used to determine the concentration of the target fence based on the third cumulative days and the fourth cumulative days if the third cumulative days reaches the preset second threshold.
[0148] On the basis of the above device, optionally, the device further includes a level value determination unit and a level value update unit. The level value determination unit is used to obtain, for the indicator data, a first level value when the same terminal device is in a serving cell and a second level value when the same terminal device is in a neighboring cell; the level value update unit is used to determine a level relative value based on the first level value and the second level value, and update the second level value in the indicator data based on the level relative value.
[0149] The positioning result determination device provided in the embodiment of the present invention can execute the positioning result determination method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.
[0150] Embodiment 7
[0151] Fig. 9 1 is a schematic diagram of the structure of an electronic device that implements the method for determining the positioning result of an embodiment of the present invention. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.
[0152] like Fig. 9As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.
[0153] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.
[0154] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as a method for determining a positioning result.
[0155] In some embodiments, the method for determining the positioning result may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the method for determining the positioning result described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to execute the method for determining the positioning result in any other appropriate manner (e.g., by means of firmware).
[0156] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.
[0157] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.
[0158] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to an object; and a keyboard and a pointing device (e.g., a mouse or trackball) through which an object can provide input to the electronic device. Other types of devices may also be used to provide interaction with an object; for example, the feedback provided to the object may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from an object may be received in any form (including acoustic input, voice input, or tactile input).
[0159] The systems and techniques described herein may be implemented in a computing system that includes a backend component (e.g., as a data server), or a computing system that includes a middleware component (e.g., an application server), or a computing system that includes a frontend component (e.g., an object computer having a graphical object interface or a web browser through which the object can interact with an implementation of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.
[0160] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.
[0161] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.
[0162] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims
1. A method for determining a positioning result, characterized in that: include: Acquiring location information of a target object based on at least two positioning methods; For each location information obtained by the positioning method, determine the confidence assessment feature corresponding to the location information, input the confidence assessment feature into a pre-trained confidence determination model, and obtain the confidence of the location information; wherein different confidence determination models are trained based on confidence sample features corresponding to the location information determined by different positioning methods and confidence labels corresponding to the confidence sample features; Based on each of the confidence levels, determining a target positioning result corresponding to the target object from all of the position information; The determining of the confidence assessment feature corresponding to the location information comprises: determining the confidence assessment feature corresponding to the location information based on at least one of the location information, a measurement report reported by a terminal device of the target object, and predetermined map data; The method also includes: when the positioning method includes a positioning method based on preset indicator features, obtaining geographic location information of at least two objects determined in a positioning method based on a broadband address, and determining the confidence of each of the geographic location information; based on the confidence of each of the geographic location information and a preset first threshold, determining the feature objects to be collected from the at least two objects; determining indicator data corresponding to the preset indicator from the measurement report reported by the terminal device of each of the feature objects to be collected; determining confidence sample features based on the indicator data and the concentration of at least one predetermined target fence; and training a confidence determination model to be trained based on the confidence sample features and the confidence labels corresponding to the confidence sample features to obtain a trained confidence determination model.
2. The method according to claim 1, characterized in that The determining, based on at least one of the location information, a measurement report reported by a terminal device of the target object, and predetermined map data, a confidence assessment feature corresponding to the location information includes: In the case where the positioning method includes a positioning method based on a broadband address, determining a first electronic fence based on predetermined map data and the location information, and determining a first shortest distance from the location information to the first electronic fence; Determine at least one serving cell and a cell location of the serving cell based on a measurement report reported by a terminal device of the target object; wherein the measurement report includes location information of at least one serving cell to be selected; A confidence assessment feature corresponding to the location information is determined based on the first closest distance, the location deviation between each of the cell locations and the location information, and the similarity between the location information and the broadband address of the target object.
3. The method according to claim 1, characterized in that The determining, based on at least one of the location information, a measurement report reported by a terminal device of the target object, and predetermined map data, a confidence assessment feature corresponding to the location information includes: In the case where the positioning method includes a positioning method based on an indoor distribution system, determining a second electronic fence based on predetermined map data and the location information, and determining a second closest distance from the location information to the second electronic fence; Determine, based on a measurement report reported by a terminal device of the target object, a time advance between the terminal device and a base station and a first cumulative number of days that the location information is located in the second electronic fence; wherein the measurement report includes at least one time advance; A confidence assessment feature corresponding to the location information is determined based on the second shortest distance, the time advance, and the first cumulative number of days.
4. The method according to claim 1, characterized in that: The determining, based on at least one of the location information, a measurement report reported by a terminal device of the target object, and predetermined map data, a confidence assessment feature corresponding to the location information includes: In the case where the positioning method includes a positioning method of minimizing route measurement, a third electronic fence is determined based on predetermined map data and the position information, and a third closest distance from the position information to the third electronic fence is determined; Determine, based on the measurement report reported by the terminal device of the target object, a second accumulated number of days that the location information is located in the third electronic fence; Based on the location information, the third closest distance, and the second cumulative number of days, a confidence assessment feature corresponding to the location information is determined.
5. The method according to claim 1, characterized in that The determining, based on the measurement report reported by the terminal device of the target object, a confidence assessment feature corresponding to the location information includes: In the case where the positioning method includes a positioning method based on a preset indicator feature, target attribute data corresponding to the preset indicator is determined based on a measurement report reported by a terminal device of the target object; wherein the preset indicator at least includes a target location where the terminal device is located and a time advance between the terminal device and a base station; the target location includes a serving cell and a neighboring cell; Based on the target attribute data, confidence assessment features corresponding to the location information are determined.
6. The method according to claim 1, characterized in that Before determining the confidence sample feature based on the indicator data and the concentration of at least one predetermined target fence, the method further includes: For a single target fence, determining a fence surrounding area corresponding to the target fence; Determine a third cumulative number of days during which the terminal location is located within the target fence and a fourth cumulative number of days during which the terminal location is located in an area surrounding the fence within a preset time period; If the third accumulated number of days reaches a preset second threshold, the concentration degree of the target fence is determined based on the third accumulated number of days and the fourth accumulated number of days.
7. The method according to claim 1, characterized in that After determining the indicator data corresponding to the preset indicator, the method further includes: For the indicator data, obtaining a first level value when the same terminal device is in a serving cell and a second level value when the same terminal device is in a neighboring cell; A level relative value is determined based on the first level value and the second level value, and the second level value in the indicator data is updated based on the level relative value.
8. A device for determining positioning results, characterized in that: include: A location information acquisition module, used to acquire location information of a target object based on at least two positioning methods; A confidence determination module, for determining, for each location information obtained by the positioning method, a confidence assessment feature corresponding to the location information, and inputting the confidence assessment feature into a pre-trained confidence determination model to obtain the confidence of the location information; wherein different confidence determination models are trained based on confidence sample features corresponding to the positioning information determined by different positioning methods and confidence labels corresponding to the confidence sample features; A target positioning result determination module, used to determine a target positioning result corresponding to the target object from all the position information based on each of the confidence levels; The confidence determination module includes: a confidence assessment feature determination unit, configured to determine a confidence assessment feature corresponding to the location information based on at least one of the location information, a measurement report reported by a terminal device of the target object, and predetermined map data; The device also includes: a geographic location information determination unit, which is used to obtain the geographic location information of at least two objects determined in a broadband address-based positioning method when the positioning method includes a positioning method based on preset indicator features, and determine the confidence of each of the geographic location information; a feature object determination unit to be collected, which is used to determine the feature object to be collected from the at least two objects based on the confidence of each of the geographic location information and a preset first threshold; an indicator data determination unit, which is used to determine the indicator data corresponding to the preset indicator from the measurement report reported by the terminal device of each of the feature objects to be collected; a confidence sample feature determination unit, which is used to determine the confidence sample feature based on the indicator data and the predetermined concentration of at least one target fence; a model determination unit, which is used to train the confidence determination model to be trained based on the confidence sample feature and the confidence label corresponding to the confidence sample feature to obtain a trained confidence determination model.
Citation Information
Patent Citations
Neighbor cell optimization method and equipment
CN111787581A
Object geographic position data determination method and device, equipment and storage medium
CN112232444A
Target identification method, system and device based on binocular camera and storage medium
CN112967283A
Method and device for determining arrival point, and program product
CN114821211A
Method and device for classifying a road
DE102021207185A1
